SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC On-Demand

Deep Learning and AI
Presentation
Media
Keynote
Jensen Huang (NVIDIA)
Don't miss this keynote from NVIDIA Founder & CEO, Jensen Huang, as he speaks on the future of computing.  ...Read More

Don't miss this keynote from NVIDIA Founder & CEO, Jensen Huang, as he speaks on the future of computing. 

  Back
 
Keywords:
Deep Learning and AI, Autonomous Vehicles, Self-Driving Cars, Data Center and Cloud Infrastructure, GTC Europe 2017 - ID 23000
Streaming:
AI for In-Vehicle Applications
Presentation
Media
A Single-Operator Command-Control of an Autonomous Swarm Routing System for Real-Time Surveillance
Kyriacos Antoniades (ICARUS & DAEDALUS LTD)
Our aim is to achieve autonomous command and control of a swarm of drones for a single operator, with the objectives of achieving military, commercial and consumer effect across the electromagnetic and acoustic spectrum, to support effective swa ...Read More

Our aim is to achieve autonomous command and control of a swarm of drones for a single operator, with the objectives of achieving military, commercial and consumer effect across the electromagnetic and acoustic spectrum, to support effective swarm mapping, tracking and networking capabilities in a dynamic environment. Icarus & Daedalus innovation brings technological disruption, by looking at a swarm of drones as a collective real time autonomous security and surveillance service, ultimately replacing manned surveillance. Our unique solution is made possible with our scientific algorithmic breakthrough in achieving real time and autonomous swarm routing, which until now was not possible. Such systems were predicted for the next 50 years, we believe this has been shorten to 5 years.

  Back
 
Keywords:
AI for In-Vehicle Applications, Algorithms and Numerical Techniques, Computer Vision and Machine Vision, GTC Europe 2017 - ID P23033
 
Tronis meets Truck: How virtual reality leverages real prototyping of autonomous vehicles
Karl KUFIETA (TWT SCIENCE AND INNOVATION), Michael DITZE (TWT SCIENCE AND INNOVATION)
This talk will describe the process of developing autonomous driving directly from the virtual environment TRONIS, a high resolution virtual environment for prototyping and safeguarding highly automated and autonomous driving functions exploitin ...Read More

This talk will describe the process of developing autonomous driving directly from the virtual environment TRONIS, a high resolution virtual environment for prototyping and safeguarding highly automated and autonomous driving functions exploiting a state of the art gaming engine as introduced by UNREAL. Well showcase this process on a real RC-model with High-End NVIDIA hardware targeting self-driving capabilities on a real world Truck. With the help of TRONIS we make early decisions on sensor configurations e.g. camera, sensor positions and deployed algorithms. The development team works on independent instances of the virtual car which build the foundation for multiple experimental setups.

  Back
 
Keywords:
AI for In-Vehicle Applications, Self-Driving Cars, Video and Image Processing, GTC Europe 2017 - ID 23318
Download:
 
Deep learning in MATLAB: From concept to embedded code
Girish Venkataramani (MATHWORKS), Bill CHOU (MATHWORKS), Alexander Schreiber (MATHWORKS)
Learn how to adopt a MATLAB-centric workflow to design, develop, and deploy computer vision and deep learning applications on to GPUs whether on your desktop, a cluster, or on embedded Tegra platforms. The workflow starts with algorithm design i ...Read More

Learn how to adopt a MATLAB-centric workflow to design, develop, and deploy computer vision and deep learning applications on to GPUs whether on your desktop, a cluster, or on embedded Tegra platforms. The workflow starts with algorithm design in MATLAB. The deep learning network is defined in MATLAB and is trained using MATLAB's GPU and parallel computing support. Then, the trained network is augmented with traditional computer vision techniques and the application can be verified in MATLAB. Finally, a compiler auto-generates portable and optimized CUDA code from the MATLAB algorithm, which can be cross-compiled to Tegra. Performance benchmark for Alexnet inference shows that the auto-generated CUDA code is ~2.5x faster than mxNet, ~5x faster than Caffe2 and is ~7x faster than TensorFlow.

  Back
 
Keywords:
AI for In-Vehicle Applications, Programming Languages, Computer Vision and Machine Vision, GTC Europe 2017 - ID 23321
Download:
 
Designing GPU-accelerated applications with real-time multisensor frameworks
Xavier ROUAH (INTEMPORA)
As embedded software in intelligent vehicles becomes more and more complex, it becomes critical to automakers and suppliers to use advanced and efficient software solutions. Learn how to dramatically reduces development cycles and how to simplify the ...Read More
As embedded software in intelligent vehicles becomes more and more complex, it becomes critical to automakers and suppliers to use advanced and efficient software solutions. Learn how to dramatically reduces development cycles and how to simplify the deployment of critical real-time applications on embedded targets. In this presentation we will show how RTMaps embedded facilitates porting design from early prototyping stages on PCs down to the most recent ECUs designed for production. RTMaps is a component based software which facilitates the design and the execution of ADAS and HAD applications. It offers an easy-to use drag-and-drop approach for GPU-based computer-vision and AI systems, including an integration of the NVIDIA DriveWorks software modules as independent building-block.  Back
 
Keywords:
AI for In-Vehicle Applications, Self-Driving Cars, HPC and AI, GTC Europe 2017 - ID 23106
Download:
 
Extensible and Verifiable Nets for Autonomous Driving
Gijs Dubbelman (EINDHOVEN UNIVERSITY OF TECHNOLOGY)
A key technology challenge in computer vision for Autonomous Driving is semantic segmentation of images in a video stream, for which fully-convolutional neural networks (FCNN) are the state-of-the-art. In this research, we explore the functional ...Read More

A key technology challenge in computer vision for Autonomous Driving is semantic segmentation of images in a video stream, for which fully-convolutional neural networks (FCNN) are the state-of-the-art. In this research, we explore the functional and non-functional performance of using a hierarchical classifier head for the FCNN versus using a single flat classifier head. Our experiments are conducted and evaluated on the Cityscapes dataset. On basis of the results, we argue that using a hierarchical classifier head for the FCNN can have specific advantages for autonomous driving. Furthermore, we show real-time usage of our network on the DRIVE PX 2 platform.

  Back
 
Keywords:
AI for In-Vehicle Applications, GTC Europe 2017 - ID 23215
Download:
 
Augmented Reality for Navigation and Informational ADAS
Sergii Bykov (APOSTERA GMBH)
Learn how combining machine learning and computer vision with GPU computing helps to create a next-generation informational ADAS experience. This talk will present a real-time software solution that encompasses a set of advanced algorithms to cr ...Read More

Learn how combining machine learning and computer vision with GPU computing helps to create a next-generation informational ADAS experience. This talk will present a real-time software solution that encompasses a set of advanced algorithms to create an augmented reality for the driver, utilizing vehicle sensors, map data, telematics, and navigation guidance. The broad range of features includes augmented navigation, visualization for cases of advanced parking assistance, adaptive cruise control and lane keeping, driver infographics, driver health monitoring, support in low visibility. Our approach augments driver's visual reality with supplementary objects in real time, and works with various output devices such as head unit displays, digital clusters, and head-up displays.

  Back
 
Keywords:
AI for In-Vehicle Applications, Self-Driving Cars, Computer Vision and Machine Vision, GTC Europe 2017 - ID 23270
Download:
 
Using Virtualization to Accelerate the Development of ADAS and Automated Driving Functions
Dominik DöRR (IPG AUTOMOTIVE GMBH)
The growing range of functions of ADAS and automated systems in vehicles as well as the progressive change towards agile development processes require efficient test. Testing and validation within simulation are indispensable for this as real pr ...Read More

The growing range of functions of ADAS and automated systems in vehicles as well as the progressive change towards agile development processes require efficient test. Testing and validation within simulation are indispensable for this as real prototypes are not available at all times and the test catalog can be driven repeatedly and reproducibly. This paper presents different approaches to be used in simulation in order to increase the efficiency of development and testing for different areas of application. This comprises the use of virtual prototypes, the utilization of sensor models and the reuse of test scenarios throughout the entire development process, which may also be applied to train artificial intelligence.

  Back
 
Keywords:
AI for In-Vehicle Applications, Intelligent Machines and IoT, Self-Driving Cars, GTC Europe 2017 - ID 23293
Download:
 
Adrenaline Fueled Development: Racing with Autonomous Vehicles
Jendrik Jördening (AKKA GERMANY), Anthony NAVARRO (UDACITY)
This talk details a team of 17 Udacity Self-Driving Car students as they attempted to apply deep learning algorithms to win an autonomous vehicle race. At the 2017 Self Racing Cars event held at Thunderhill Raceway in California, the team receiv ...Read More

This talk details a team of 17 Udacity Self-Driving Car students as they attempted to apply deep learning algorithms to win an autonomous vehicle race. At the 2017 Self Racing Cars event held at Thunderhill Raceway in California, the team received a car and had two days before the start of the event to work on the car. In this time, we developed a neural network using Keras and Tensorflow which steered the car based on the input from just one front-facing camera in order to navigate all turns on the racetrack. We will discuss the events leading up to the race, development methods used, and future plans including the use of ROS and semantic segmentation.

  Back
 
Keywords:
AI for In-Vehicle Applications, Self-Driving Cars, Video and Image Processing, GTC Europe 2017 - ID 23317
Download:
 
ADAS Development using Advanced Real-Time All-in-the-Loop Simulators
Roberto DE VECCHI (VI-GRADE), Enrico BUSTO (ADDFOR S.P.A.), Guido BAIRATI (VI-GRADE)
This presentation shows how driving simulators together with DNN algorithms can be used in order to streamline and facilitate the development of ADAS and Autonomous Vehicle systems. Driving Simulators provide an excellent tool to develop, test a ...Read More

This presentation shows how driving simulators together with DNN algorithms can be used in order to streamline and facilitate the development of ADAS and Autonomous Vehicle systems. Driving Simulators provide an excellent tool to develop, test and validate control systems for automotive industry. Testing ADAS systems on the driving simulator makes it safer, more affordable and repeateble. This session will focus on a special application in which NVIDIA DRIVE PX 2 has been interfaced with a camera and put in the loop on a driving simulator. Object recognition algorithms have been developed in order to develop and test a Lane Keeping Assist (LKA) system. The robustness of the system can be tested on the simulator by altering the environmental conditions and vehicle parameters.

  Back
 
Keywords:
AI for In-Vehicle Applications, Self-Driving Cars, Computer Aided Engineering, GTC Europe 2017 - ID 23085
Download:
 
Integrated safety for autonomous driving
Torsten Gollewski (ZF FRIEDRICHSHAFEN AG)
ZF sees itself as obligated to fulfill the Vision Zero traffic which causes neither accidents nor emissions. Although self-driving vehicles are expected to significantly reduce accidents in the future, they nevertheless need to be designed to move ...Read More
ZF sees itself as obligated to fulfill the Vision Zero traffic which causes neither accidents nor emissions. Although self-driving vehicles are expected to significantly reduce accidents in the future, they nevertheless need to be designed to move in traffic that will continue to be dominated by non-autonomous vehicles, which represent potential participants in an accident. ZF sees two development steps: In the first step, advanced passive and active safety systems must become enablers of autonomous driving. In the second step, networked traffic can prevent more and more accidents. Network integration and autonomous driving are necessary if the numbers of traffic deaths worldwide are to be reduced drastically in the coming decades.  Back
 
Keywords:
AI for In-Vehicle Applications, Self-Driving Cars, GTC Europe 2017 - ID 23111
 
The learning and intelligent vehicle - a human centric approach to save more lives
Ola Boström (AUTOLIV)
Thanks to recent breakthroughs in AI vehicles will learn and collaborate with humans. There will be a steering wheel in the majority of vehicles for a long time. Therefore a human centric approach is needed in order to save more lives in the tra ...Read More

Thanks to recent breakthroughs in AI vehicles will learn and collaborate with humans. There will be a steering wheel in the majority of vehicles for a long time. Therefore a human centric approach is needed in order to save more lives in the traffic, that is a safe combination of AI and UI.

  Back
 
Keywords:
AI for In-Vehicle Applications, Self-Driving Cars, GTC Europe 2017 - ID 23124
Download:
 
Accelerating the TomTom HD Map flywheel
Willem STRIJBOSCH (TOMTOM)
TomTom is leading in HD Maps in coverage and number of OEMs working with our HD Map. Our multi-source, multi-sensor approach leads to HD maps that have greater coverage, are more richly attributed, and have higher quality than single-source, sin ...Read More

TomTom is leading in HD Maps in coverage and number of OEMs working with our HD Map. Our multi-source, multi-sensor approach leads to HD maps that have greater coverage, are more richly attributed, and have higher quality than single-source, single-sensor maps. Hear how were weaving in more and more sources, such as AI-intensive video processing, into our map making to accelerate towards our goal of real-time and highly precise maps for safer and more comfortable driving.

  Back
 
Keywords:
AI for In-Vehicle Applications, HD Mapping, Self-Driving Cars, GTC Europe 2017 - ID 23130
Download:
 
Application of Artificial Intelligence at Continental
Umut Ikibas (CONTINENTAL AUTOMOTIVE GMBH), Stefan VOGET (CONTINENTAL AUTOMOTIVE GMBH)
In our presentation we will focus on the automotive electronic control units while giving a rough overview on the others. During the presentation we will show the development process of one of our neural networks using the NVIDIA toolchain and hardwa ...Read More
In our presentation we will focus on the automotive electronic control units while giving a rough overview on the others. During the presentation we will show the development process of one of our neural networks using the NVIDIA toolchain and hardware for training and deployment. Using this example we want to highlight the necessary actions in standardization of e.g. labels, data-interaction and interfaces we need to face in the near future.  Back
 
Keywords:
AI for In-Vehicle Applications, Embedded & Robotics, Computer Vision and Machine Vision, GTC Europe 2017 - ID 23156
Download:
 
Automated and Tele-operated Cooperative Driving in Berlin
Ilja RADUSCH (FRAUNHOFER FOKUS)
Level 5 automated driving is a unique challenge given there is no driver in the vehicle, so vehicles may need to be remotely rescued. Remote tele-operation can not rely on all local sensor data being transmitted to the operation center. Instead machi ...Read More
Level 5 automated driving is a unique challenge given there is no driver in the vehicle, so vehicles may need to be remotely rescued. Remote tele-operation can not rely on all local sensor data being transmitted to the operation center. Instead machine learning is used for smart scene reconstruction with minimal data requirements. This session will outline the activities of automated and cooperative driving in Berlin.  Back
 
Keywords:
AI for In-Vehicle Applications, HD Mapping, Self-Driving Cars, GTC Europe 2017 - ID 23173
 
Visual Perception for Autonomous Driving on the NVIDIA DrivePX2 and using SYNTHIA
Juan Carlos Moure (UNIVERSITY AUTONOMA OF BARCELONA), Antonio ESPINOSA (UNIVERSITY AUTONOMA OF BARCELONA)
We present our experience of running computationally intensive camera-based perception algorithms on NVIDIA GPUs. Geometric (depth) and semantic (classification) information is fused in the form of semantic stixels, which provide a rich and comp ...Read More

We present our experience of running computationally intensive camera-based perception algorithms on NVIDIA GPUs. Geometric (depth) and semantic (classification) information is fused in the form of semantic stixels, which provide a rich and compact representation of the traffic scene. We present some strategies to reduce the computational complexity of the algorithms. Using synthetic data generated by the SYNTHIA tool, including slanted roads from a simulation of San Francisco city, we evaluate performance latencies and frame rates on a DrivePX2-based platform.

  Back
 
Keywords:
AI for In-Vehicle Applications, Computer Vision and Machine Vision, HPC and AI, GTC Europe 2017 - ID 23196
Download:
 
Deep Learning for Human-centered Video Analysis Solutions
Christian THURAU (TWENTY BILLION NEURONS)
Learn how deep learning is used to process video streams to analyse human behaviour in real-time. We will detail our solution to recognise fine-grained movement patterns of people how they perform everyday actions like e.g. walking, eating, shak ...Read More

Learn how deep learning is used to process video streams to analyse human behaviour in real-time. We will detail our solution to recognise fine-grained movement patterns of people how they perform everyday actions like e.g. walking, eating, shaking hands, talking to each other. The novelty of our technical solution is that our system learns these capabilities from watching lots of video snippets showing such actions. This is exciting because very different applications can be realised with the same algorithms as we follow a purely data-driven, machine learning approach. We will explain what new types of deep neural networks we created and how we employ our Crowd Acting (tm) platform to cost-efficiently acquire hundred thousands videos for that.

  Back
 
Keywords:
AI for In-Vehicle Applications, Intelligent Video Analytics and Smart Cities, Video and Image Processing, GTC Europe 2017 - ID 23233
Download:
 
Take It To The Track - Autonomous Racing
Benjamin EWERT (SCHANZER RACING), Daniel GÖRNER (FÖRDERVEREIN GREENTEAM STUTTGART E.V.), Florian KECK (KA-RACEING E.V.)
This talk will present the recent achievements in the field autonomous racing, specifically track detection and evaluation based on cameras. In August 2016 the FSG announced a class for self engineered, self racing cars. Track detection, driven line ...Read More
This talk will present the recent achievements in the field autonomous racing, specifically track detection and evaluation based on cameras. In August 2016 the FSG announced a class for self engineered, self racing cars. Track detection, driven line evaluation, controllers and the vision system all run on the NVIDIA DRIVE PX 2 with four cameras connected to it. The 3 sponsored teams from NVIDIA will share their success.  Back
 
Keywords:
AI for In-Vehicle Applications, Self-Driving Cars, GTC Europe 2017 - ID 23309
 
AI for driving monitoring in the future
Martin KRANTZ (SMART EYE)
2017 is the year when the first driver monitoring systems goes into series production with global automotive OEMs. It will be a mainstay as a vital part in most level 3 automated cars but it also has unique stand alone applications such as drows ...Read More

2017 is the year when the first driver monitoring systems goes into series production with global automotive OEMs. It will be a mainstay as a vital part in most level 3 automated cars but it also has unique stand alone applications such as drowsiness and attention, functions that adress approximately half of all traffic accidents. Starting in 2019 there will be more advanced systems going to the market based on improvements in hardware such as high resolution cameras and GPU. Around 2022 there is a third generation of in-car AI to be expected as the hardware will consist of multiple HD cameras running on the latest GPUs.

  Back
 
Keywords:
AI for In-Vehicle Applications, Self-Driving Cars, Computer Vision and Machine Vision, GTC Europe 2017 - ID 23347
Download:
 
Artificial Intelligence for Cognitive Vehicles - Applications and Technologies
Florian NETTER (AUDI AG)
Artificial Intelligence (AI) is an emerging technology that enables unprecedented applications in vehicles but requires a new mind-set for automotive software development. While conventional software development aims to distil expert knowledge into c ...Read More
Artificial Intelligence (AI) is an emerging technology that enables unprecedented applications in vehicles but requires a new mind-set for automotive software development. While conventional software development aims to distil expert knowledge into code, AI is data-driven and works best when learning doesn''t stop after a product launch. In order to realize this, both vehicles and backend must be empowered to satisfy AI''s massive demands towards computational performance and connectivity. This session discusses fundamental key concepts for AI in vehicles, hardware aspects and system requirements.  Back
 
Keywords:
AI for In-Vehicle Applications, Data Center and Cloud Infrastructure, Self-Driving Cars, GTC Europe 2017 - ID 23368
 
Learned driving
Urs MULLER (NVIDIA)
In our NVIDIA lab in New Jersey we taught a deep convolutional neural network (DNN) to drive a car by observing human drivers and emulating their behavior. We found that these networks can learn more aspects of the driving task than is commonly ...Read More

In our NVIDIA lab in New Jersey we taught a deep convolutional neural network (DNN) to drive a car by observing human drivers and emulating their behavior. We found that these networks can learn more aspects of the driving task than is commonly learned today. We present examples of learned lane keeping, lane changes, and turns. We also introduce tools to visualize the internal information processing of the neural network and discuss the results.

  Back
 
Keywords:
AI for In-Vehicle Applications, Embedded & Robotics, GTC Europe 2017 - ID 23385
Download:
 
Deploying Embedded Computer Vision systems on Military Ground Vehicles
Ross NEWMAN (ABACO)
GPUs can significantly enhance the capabilities of Military Ground Vehicles. In this session we will discuss the challenges facing the integrator of real time vision systems in the Military applications. From video streaming and military streami ...Read More

GPUs can significantly enhance the capabilities of Military Ground Vehicles. In this session we will discuss the challenges facing the integrator of real time vision systems in the Military applications. From video streaming and military streaming protocols through to deploying vision systems for 360 degree situational awareness with AI capabilities. GPUs are being used for enhanced autonomy and in the defence sector and across the board from Ground Vehicles through to Naval and Air applications. Each application space presenting its own challenges through to deployment. Come and find out how the defence industry is addressing these challenges and where the future potential of GPU enabled platforms lie.

  Back
 
Keywords:
AI for In-Vehicle Applications, Embedded & Robotics, Video and Image Processing, GTC Europe 2017 - ID 23390
Download:
 
Designing for Utopia
Lewis Horne (UNITI SWEDEN AB)
The autonomous electric car revolution is here and a bright clean future awaits. Yet as we shift to this fundamentally different technology, it becomes clear that perhaps the entire vehicle deserves a rethink. This means not just adding powerful ...Read More

The autonomous electric car revolution is here and a bright clean future awaits. Yet as we shift to this fundamentally different technology, it becomes clear that perhaps the entire vehicle deserves a rethink. This means not just adding powerful computers to outdated vehicle platforms, but instead redesigning the agile device, for this very different future. This process doesnt start with the mechanical structure of yesteryear, instead it starts with the GPU.

  Back
 
Keywords:
AI for In-Vehicle Applications, GTC Europe 2017 - ID 23439
Download:
 
Deep Learning for Autonomous Driving
Sepp HOCHREITER (JOHANNES KEPLER UNIVERSITY LINZ), Markus HOFMARCHER (INSTITUTE OF BIOINFORMATICS AT THE JOHANNES KEPLER UNIVERSITY LINZ)
Deep Learning has emerged as the most successful field of machine learning with overwhelming success in industrial speech, language and vision benchmarks. Consequently it evolved into the central field of research for IT giants like Google, face ...Read More

Deep Learning has emerged as the most successful field of machine learning with overwhelming success in industrial speech, language and vision benchmarks. Consequently it evolved into the central field of research for IT giants like Google, facebook, Microsoft, Baidu, and Amazon. Deep Learning is founded on novel neural network techniques, the recent availability of very fast computers, and massive data sets. In its core, Deep Learning discovers multiple levels of abstract representations of the input. Currently the development of self-driving cars is one of the major technological challenges across automotive companies. We apply Deep Learning to improve real-time video data analysis for autonomous vehicles, in particular, semantic segmentation.

  Back
 
Keywords:
AI for In-Vehicle Applications, GTC Europe 2017 - ID 23472
Download:
Accelerated Analytics
Presentation
Media
Fastest GPU-Based OLAP and Data Mining: Big Data Analytics on DGX
Roman Raevsky (POLYMATICA)
Polymatica is an OLAP and Data Mining server with hybrid CPU+GPU architecture which turns any analytical work on billions-records data volumes into a proactive process with no waitings. Polymatica architecture uses NVIDIA Multi-GPU (i.e. in DGX- ...Read More

Polymatica is an OLAP and Data Mining server with hybrid CPU+GPU architecture which turns any analytical work on billions-records data volumes into a proactive process with no waitings. Polymatica architecture uses NVIDIA Multi-GPU (i.e. in DGX-1) in critical operations with billions of raw business data records. This allows to eliminate pauses and accelerate the speed of analytical operations for up to hundred times. You'll see the performance difference on the example of the real analytical process in retail on different hardware: 1) CPU-only calculations on 2*Intel Xeon, no GPU; 2) 2*Intel Xeon + single Tesla P100; 3) DGX-1: 2*Intel Xeon + 8*Tesla P100. Polymatica on DGX-1 become the fastest OLAP and Data Mining engine allowing advanced analytics on datasets of billions of records.

  Back
 
Keywords:
Accelerated Analytics, Algorithms and Numerical Techniques, HPC and AI, GTC Europe 2017 - ID 23164
Download:
 
Building Brains - Parallelisation strategies of large-scale deep learning neural networks on parallel scale out architectures like ApacheSpark using GPUs
Romeo Kienzler (IBM WATSON IOT)
New deep learning frameworks are being developed on a monthly basis. For most of them, the inventors did not have scale-out parallelisation in mind. ApacheSpark and other data parallel frameworks, on the other hand, are becoming the de-facto sta ...Read More

New deep learning frameworks are being developed on a monthly basis. For most of them, the inventors did not have scale-out parallelisation in mind. ApacheSpark and other data parallel frameworks, on the other hand, are becoming the de-facto standard for BigData analysis. In this talk, we will have a look at different deep learning frameworks and their parallelisation strategies on GPUs and ApacheSpark. Well start with DeepLearning4J and ApacheSystemML as first class citizens. We will then have a look at TensorSpark and TensorFrames and finish with CaffeOnSpark to explain concepts like Inter- and Intra-model parallelism, distributed Cross-Validation and Jeff Dean style parameter averaging.

  Back
 
Keywords:
Accelerated Analytics, Algorithms and Numerical Techniques, HPC and Supercomputing, GTC Europe 2017 - ID 23201
Download:
 
Distributed Deep Learning on MapR Converged Data Platform with Heterogeneous NVIDIA GPU clusters
William Cairns (MAPR TECHNOLOGIES)
We utilize a MapR converged data platform to serve as the data layer to provide distributed file system, key-value storage and streams to store and build the data pipeline. On top of that, we use Kubernetes as an orchestration layer to manage th ...Read More

We utilize a MapR converged data platform to serve as the data layer to provide distributed file system, key-value storage and streams to store and build the data pipeline. On top of that, we use Kubernetes as an orchestration layer to manage the containers to train and deploy deep learning models, as well as serve the deep learning models in the form of containers.

  Back
 
Keywords:
Accelerated Analytics, Data Center and Cloud Infrastructure, Tools and Libraries, GTC Europe 2017 - ID 23223
Download:
 
Neural Network for Nanoscience: Scanning Electron Microscope Image Recognition
Giuseppe Piero Brandino (EXACT LAB S.R.L.)
This session will present an overview on how we recently applied modern deep learning techniques to the wide area of nanoscience. We will focus on deep convolutional neural network training to classify Scanning Electron Microscope (SEM) images a ...Read More

This session will present an overview on how we recently applied modern deep learning techniques to the wide area of nanoscience. We will focus on deep convolutional neural network training to classify Scanning Electron Microscope (SEM) images at the nanoscale, discussing first the issues we faced, and then how we solved them by improving the standard deep learning tools. This session aims to introduce a new promising and stimulating field of research that implements deep learning techniques in the nanoscience domain, with the final aim to provide researchers with advanced and innovative tools. These will contribute to improve the scientific research in the boosting field of experimental and computational nanoscience.

  Back
 
Keywords:
Accelerated Analytics, Video and Image Processing, GTC Europe 2017 - ID 23228
Download:
 
Visualizing and Interrogating Black box AI Models with GPU Enabled Architecture
Zach Izham (VOLKSWAGEN), Asghar GHORBANI (VOLKSWAGEN)
In the world of analytics and AI for many, GPU-accelerated analytics is equivalent to speeding up training time. The question, however, remains is how one interprets such highly complex black box models? How these models can help decision-making ...Read More

In the world of analytics and AI for many, GPU-accelerated analytics is equivalent to speeding up training time. The question, however, remains is how one interprets such highly complex black box models? How these models can help decision-making? Well discuss and present here a GPU based architecture to not only accelerate training the models but also use the GPU based databases and visual analytics to render billions of rows to solve the challenges of interpreting these black box models. With the advent of algorithms, databases and visualization tools, all based on a GPU architecture a solution like this has become more accessible. Interactive visualization of the model, based on partial dependence analysis, is one approach to interpret these opaque models and is our focus here.

  Back
 
Keywords:
Accelerated Analytics, Algorithms and Numerical Techniques, GTC Europe 2017 - ID 23244
Download:
 
Scaling on One Node: Hybrid Engines With Multi-GPU on In-Memory Database Queries
Peter Strohm (JEDOX AG)
Learn how large requests on big datasets, like production or finance data, can benefit from hybrid engine approaches for calculating on in-memory databases. While hybrid architectures are state-of-the-art in specialized calculation scenarios (e. ...Read More

Learn how large requests on big datasets, like production or finance data, can benefit from hybrid engine approaches for calculating on in-memory databases. While hybrid architectures are state-of-the-art in specialized calculation scenarios (e.g., linear algebra), multi-GPU or even multicore usage in database servers is still far from everyday use. In general, the approach to handle requests on large datasets would be scaling the database resources by adding new hardware nodes to the compute cluster. We use intelligent request planning and load balancing to distribute the calculations to multi-GPU and multicore engines in one node. These calculation engines are specifically designed for handling hundreds of millions of cells in parallel with minimal merging overhead.

  Back
 
Keywords:
Accelerated Analytics, Performance Optimization, HPC and AI, GTC Europe 2017 - ID 23294
Download:
 
Deep Learning – Accelerating the NLP Journey
Toby LEHEUP (CREDIT SUISSE), Shahzad Chohan (CREDIT SUISSE)
Discover how Credit Suisse has implemented Deep Learning in eCommunications Surveillance, and how moving to GPU-accelerated models has yielded significant business value. The solution works on unstructured data and leverages bleeding-edge Natura ...Read More

Discover how Credit Suisse has implemented Deep Learning in eCommunications Surveillance, and how moving to GPU-accelerated models has yielded significant business value. The solution works on unstructured data and leverages bleeding-edge Natural Language Processing techniques, and will be enhanced with emotion analysis running on GPU-farms.  This talk will include a demo of the functionality.    

  Back
 
Keywords:
Accelerated Analytics, Tools and Libraries, Intelligent Machines and IoT, GTC Europe 2017 - ID 23259
Download:
 
Reinforcement Learning for Railway Scheduling: Overcoming Data Sparseness through Simulations
Erik NYGREN (SBB)
Deep learning optimization in real world applications is often limited by the lack of valuable data, either due to missing labels or the sparseness of relevant events (e.g. failures, anomalies) in the dataset. We face this problem when we optimi ...Read More

Deep learning optimization in real world applications is often limited by the lack of valuable data, either due to missing labels or the sparseness of relevant events (e.g. failures, anomalies) in the dataset. We face this problem when we optimize dispatching and rerouting decisions in the Swiss railway network, where the recorded data is variable over time and only contains a few valuable events. To overcome this deficiency we use the high computational power of modern GPUs to simulate millions of physically plausible scenarios. We use this artificial data to train our deep reinforcement learning algorithms to find and evaluate novel and optimal dispatching and rerouting strategies.

  Back
 
Keywords:
Accelerated Analytics, Other, HPC and AI, GTC Europe 2017 - ID 23163
Download:
 
Brain Research: A Pathfinder for Future HPC
Dirk Pleiter (FORSCHUNGSZENTRUM JUELICH / JUELICH SUPERCOMPUTING CENTRE)
A key driver for pushing high-performance computing is the enablement of new research. One of the biggest and most exiting scientific challenge requiring high-performance computing is to decode the human brain. Many of the research topics in thi ...Read More

A key driver for pushing high-performance computing is the enablement of new research. One of the biggest and most exiting scientific challenge requiring high-performance computing is to decode the human brain. Many of the research topics in this field require scalable compute resources or the use of advance data analytics methods (including deep learning) for processing extreme scale data volumes. GPUs are a key enabling technology and we will thus focus on the opportunities for using these for computing, data analytics and visualisation. GPU-accelerated servers based on POWER processors are here of particular interest due to the tight integration of CPU and GPU using NVLink and the enhanced data transport capabilities.

  Back
 
Keywords:
Accelerated Analytics, HPC and AI, HPC and Supercomputing, GTC Europe 2017 - ID 23189
Download:
 
Optimizing, Profiling, and Deploying TensorFlow AI Models in Production with GPUs
Chris Fregly (PIPELINEAI)
Using the latest advancements from TensorFlow including the Accelerated Linear Algebra (XLA) Framework, JITundefinedAOT Compiler, and Graph Transform Tool , Ill demonstrate how to optimize, profile, and deploy TensorFlow Models in GPU-based prod ...Read More

Using the latest advancements from TensorFlow including the Accelerated Linear Algebra (XLA) Framework, JITundefinedAOT Compiler, and Graph Transform Tool , Ill demonstrate how to optimize, profile, and deploy TensorFlow Models in GPU-based production environment. This talk is 100% demo based with open source tools and completely reproducible through Docker on your own GPU cluster. In addition, I spin up a GPU cloud instance for every attendee in the audience. We go through the notebooks together as I demonstrate the process of continuously training, optimizing, deploying, and serving a TensorFlow model on a large, distributed cluster of Nvidia GPUs managed by the attendees.

  Back
 
Keywords:
Accelerated Analytics, Performance Optimization, Tools and Libraries, GTC Europe 2017 - ID 23363
Download:
 
DGX Systems: Best Practices for Deep Learning from Desk to Data Center
Markus WEBER (NVIDIA), Haiduong VO (NVIDIA)
NVIDIA DGX Systems powered by Volta deliver breakthrough performance for today''s most popular deep learning frameworks. Attend this session to hear from DGX product experts and gain insights that will help researchers, developers, and d ...Read More

NVIDIA DGX Systems powered by Volta deliver breakthrough performance for today''s most popular deep learning frameworks. Attend this session to hear from DGX product experts and gain insights that will help researchers, developers, and data science practitioners accelerate training and iterate faster than ever. Learn (1) best practices for deploying an end-to-end deep learning practice, (2) how the newest DGX systems including DGX Station address the bottlenecks impacting your data science, and (3) how DGX software including optimized deep learning frameworks give your environment a performance advantage over GPU hardware alone.

  Back
 
Keywords:
Accelerated Analytics, Computer Vision and Machine Vision, HPC and AI, GTC Europe 2017 - ID 23370
Download:
 
Caffe2: A New Lightweight, Modular, and Scalable Deep Learning Framework
Marat Dukhan (FACEBOOK), Alexander SIDOROV (FACEBOOK)
Caffe2 is a lightweight, modular, and scalable deep learning framework refactored from the previous Caffe. Caffe2 has been widely used at Facebook to enable new AI & AR experiences. This talk will be divided into two parts. In the first part ...Read More

Caffe2 is a lightweight, modular, and scalable deep learning framework refactored from the previous Caffe. Caffe2 has been widely used at Facebook to enable new AI & AR experiences. This talk will be divided into two parts. In the first part, we will explain some framework basics, the strengths of Caffe2, large scale training support and will walk you through several product use-cases at Facebook including computer vision, machine translation, speech recognition and content ranking. The second part will explain how users benefit from Caffe2''s built-in neural network model compression, fast convolution for mobile CPUs, and GPU acceleration.

  Back
 
Keywords:
Accelerated Analytics, Performance Optimization, Tools and Libraries, GTC Europe 2017 - ID 23450
Download:
Algorithms and Numerical Techniques
Presentation
Media
GPU Solver for Porous Media Two-Phase Flow Problems Using Unstructured Meshes
Jakub KlinkovskÝ (DEPARTMENT OF MATHEMATICS, FACULTY OF NUCLEAR SCIENCES AND PHYSICAL ENGINEERING, CZECH TECHNICAL UNIVERSITY IN PRAGUE)
We present a GPU accelerated solver for the numerical solution of two-phase flow in porous media based on the semi-implicit MHFE/DG scheme. The solver is implemented in the C++ language with the help of the TNL library, the CUDA framework for pa ...Read More

We present a GPU accelerated solver for the numerical solution of two-phase flow in porous media based on the semi-implicit MHFE/DG scheme. The solver is implemented in the C++ language with the help of the TNL library, the CUDA framework for parallelization on GPUs and OpenMP for parallelization on multicore CPUs. The TNL library provides a unified interface for the development of numerical solvers, which can be run on any supported architecture. Therefore, we can presentto the best of our knowledgethe first implementation of the MHFE/DG pipeline, which can run all computations on GPU. Our simulations with a modified GMRES method show a GPU speedup of more than 20x vs single-thread and about 6x vs 6-thread computations on CPU.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Computational Fluid Dynamics, HPC and AI, GTC Europe 2017 - ID P23024
 
A GPU-Accelerated RK4IP Implementation for the Simulation of Optical Transmission Systems
Marius BREHLER (TU DORTMUND)
Fiber optical long-haul transport networks form the basis of global communication, enabling the internet as we know it. A main challenge in the design of future optical networks is to satisfy the growing traffic demand. One option to solve this ...Read More

Fiber optical long-haul transport networks form the basis of global communication, enabling the internet as we know it. A main challenge in the design of future optical networks is to satisfy the growing traffic demand. One option to solve this challenge is the use of multimode fibers for so-called space-division multiplexed transmissions. To develop such new transmission systems, the simulation of the nonlinear signal propagation in the fibers has become increasingly important. We present a GPU-accelerated fourth-order Runge-Kutta in the Interaction Picture (RK4IP) method to enable the study of the propagation in those systems. Details for an efficient parallelization are revealed and speed-ups over a multicore implementation are shown.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Computational Physics, HPC and AI, GTC Europe 2017 - ID P23028
 
Batched Factorization and Inversion for Iterative Solvers
Goran Flegar (UNIVERSITY OF JAUME)
Block-Jacobi preconditioning requires the solution of a collection of small and independent linear systems. This can be realized by combining a factorization of the diagonal blocks in the preconditioner setup with a set of small triangular solve ...Read More

Block-Jacobi preconditioning requires the solution of a collection of small and independent linear systems. This can be realized by combining a factorization of the diagonal blocks in the preconditioner setup with a set of small triangular solves in the preconditioner application, or by the explicit inversion of the diagonal blocks. We present variable-size batched routines for factorization, triangular solves, and inversion, and analyze performance and efficiency in an iterative solver setting.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Performance Optimization, HPC and AI, GTC Europe 2017 - ID P23032
 
Error Corrective Boosting for Learning Fully Convolutional Networks with Limited Data
Abhijit Guha Roy (LUDWIG MAXIMILIAN UNIVERSITY, MUNICH.)
Training deep fully convolutional neural networks (F-CNNs) for image segmentation generally requires abundant labeled data. While large datasets of unlabeled image data are available in medical applications, access to manually labeled data is ve ...Read More

Training deep fully convolutional neural networks (F-CNNs) for image segmentation generally requires abundant labeled data. While large datasets of unlabeled image data are available in medical applications, access to manually labeled data is very limited. Here, we propose error corrective boosting, a method for training F-CNNs with limited annotated data using unlabeled data corpus. We address the challenging task of whole brain segmentation of MRI T1 scans into 27 classes with only 15 annotated volumes for training. Our proposed framework segments a 3D scan in 7 secs on GPU in comparison to 30 hours for the closest multi-atlas segmentation method, while reaching similar performance.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Computer Vision and Machine Vision, Medical Imaging and Radiology, GTC Europe 2017 - ID P23048
 
Fast Low-Rank Numerical Solvers on DGX-1
Hatem LTAIEF (KAUST)
Come and learn about new fast low-rank matrix computations on GPUs! By exploiting the low-rank off-diagonal block structure, we design and implement fast linear algebra operations on massively parallel hardware architectures. The main idea is to ...Read More

Come and learn about new fast low-rank matrix computations on GPUs! By exploiting the low-rank off-diagonal block structure, we design and implement fast linear algebra operations on massively parallel hardware architectures. The main idea is to refactor the numerical algorithms and the corresponding implementations by aggregating similar numerical operations in terms of highly optimized batched kernels. Applications in weather prediction, seismic imaging and material science are employed to assess the trade-off between numerical accuracy and parallel performance of these fast matrix computations compared to more traditional approaches..

  Back
 
Keywords:
Algorithms and Numerical Techniques, Tools and Libraries, HPC and AI, GTC Europe 2017 - ID 23367
Download:
 
Combining AI, RGB, and 3D for Self-Driving Cognition Systems
Yaron TANNE (VAYAVISION), Doron ELINAV (VAYAVISION)
In this session we will present how our sensor fusion and solution architecture, running on the Drive PX2 platform, provides the advanced perception needed for self driving cars. The raw data fusion of camera and LiDAR generates a high resolution 3D ...Read More
In this session we will present how our sensor fusion and solution architecture, running on the Drive PX2 platform, provides the advanced perception needed for self driving cars. The raw data fusion of camera and LiDAR generates a high resolution 3D RGBd model. In combination with AI, it detects even small obstacles such as a torn tire and rocks on the road, much better than standard classification methods such as Deep Neural Network semantic segmentation. We will also show examples of sensor fusion cognition as compared to the typical high level fusion implementation.  Back
 
Keywords:
Algorithms and Numerical Techniques, Self-Driving Cars, Video and Image Processing, GTC Europe 2017 - ID 23043
Download:
 
The Simulation of the Behavior of the Human Brain using CUDA
Pedro Valero-Lara (BARCELONA HPC and Supercomputing CENTER (BSC))
The attendees can learn about how the behavior of Human Brain is simulated by using current computers, and the different challenges which the implementation has to deal with. We cover the main steps of the simulation and the methodologies behind ...Read More

The attendees can learn about how the behavior of Human Brain is simulated by using current computers, and the different challenges which the implementation has to deal with. We cover the main steps of the simulation and the methodologies behind this simulation. In particular we highlight and focus on those transformations and optimizations carried out to achieve a good performance on NVIDIA GPUs.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Performance Optimization, HPC and AI, GTC Europe 2017 - ID 23076
Download:
 
Disrupting the Creative Industry with AI
Marco Marchesi (HAPPY FINISH LTD.), Daniel CHEETHAM (HAPPY FINISH LTD)
The talk will cover two related topics: firstly, how AI is disrupting the creative industries in which Happy Finish work and secondly, discuss a specific project example where Happy Finish created a hero campaign image for the Unilever Baby Dove ...Read More

The talk will cover two related topics: firstly, how AI is disrupting the creative industries in which Happy Finish work and secondly, discuss a specific project example where Happy Finish created a hero campaign image for the Unilever Baby Dove brand using a Generative Adversarial Network, gaining widespread media attention. Happy Finish is working on new solutions relating the machine generation of content, using AI to create campaign content for their clients. Marco and Daniel will outline their vision of how machines can collaborate with humans in the creativity process.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Media and Entertainment, Video and Image Processing, GTC Europe 2017 - ID 23103
Download:
 
Disrupting Computer Aided Engineering - Key Building Blocks of Accurate Interactive Engineering Simulations
Dirk Hartmann (SIEMENS AG, CORPORATE TECHNOLOGY)
The goal of the session is to deep dive into key technical building blocks of interactive Computer Aided Engineering (CAE) and to understand along specific prototypes how GPU computing will impact it. Considering the example of interactive desig ...Read More

The goal of the session is to deep dive into key technical building blocks of interactive Computer Aided Engineering (CAE) and to understand along specific prototypes how GPU computing will impact it. Considering the example of interactive design assistants, we will explain the ingredients of future GPU-based simulation codes: (i) multi-level voxel geometry representation from integration to finite elements, (ii) Indirect (weak) realization of boundary conditions, (iii) (non-linear) geometric multi-grid methods. By streamlining all algorithms with respects to GPU, state-of-the-art industrial solutions are outperformed by orders of magnitude in computational efficiency yet conserving accuracy. This is shown along a few prototypes towards the vision of a virtual maker space.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Computer Aided Engineering, HPC and AI, GTC Europe 2017 - ID 23113
Download:
 
Deep 3D - Machine Learning for Reconstruction and Repair of 3D Surfaces
Pascal LAUBE (HTWG KONSTANZ)
This session will give the audience a quick overview of recent developments in the field of 3D surface analysis with deep learning techniques and an insight into our approach for 3D surface repair. In recent years, deep learning methods have sho ...Read More

This session will give the audience a quick overview of recent developments in the field of 3D surface analysis with deep learning techniques and an insight into our approach for 3D surface repair. In recent years, deep learning methods have shown to be able to tackle many vision related problems with astonishing success. Compared to the application of Deep Learning for image processing, applications for geometry processing in 3D are still rare. The main reason for this is the lack of a suitable 3D representation. We present a method for 3D surface analysis in which we use different data representations and machine learning methods to repair defect or damaged 3D surfaces. After this session, you should have an idea of how to approach 3D related problems with deep learning.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Computer Aided Engineering, Computer Vision and Machine Vision, GTC Europe 2017 - ID 23152
Download:
 
Training and validating automated driving applications using physics-based sensor simulation
Martijn TIDEMAN (TASS INTERNATIONAL)
This session will cover how the PreScan simulation platform can be used to generate virtual sensor data of all sensor technologies relevant to automated driving, such as camera, radar, lidar, ultrasone, and DSRC. By generating synthetic sensor d ...Read More

This session will cover how the PreScan simulation platform can be used to generate virtual sensor data of all sensor technologies relevant to automated driving, such as camera, radar, lidar, ultrasone, and DSRC. By generating synthetic sensor data as input for deep neural networks, training for driving applications can be automated. We will cover the special requirements that virtual sensor data needs to meet in order to be suitable for training algorithms that will eventually be deployed in the real-world. In addition, we will highlight the value of injecting synthetic sensor data directly into platforms such as the NVIDIA DRIVE PX 2 for virtual validation of automated driving applications by means of Hardware-in-the-Loop (HiL) simulation.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Self-Driving Cars, Computer Vision and Machine Vision, GTC Europe 2017 - ID 23170
Download:
 
Towards an Efficient CPU--GPU Code Hybridization: a Simple Guideline for Code Optimizations on Modern Architecture with OpenACC and CUDA
Ludomir Oteski (ONERA)
Learn a simple strategy guideline to optimize applications runtime. The strategy is based on four steps and illustrated on a two-dimensional Discontinuous Galerkin solver for computational fluid dynamics on structured meshes. Starting from a CPU ...Read More

Learn a simple strategy guideline to optimize applications runtime. The strategy is based on four steps and illustrated on a two-dimensional Discontinuous Galerkin solver for computational fluid dynamics on structured meshes. Starting from a CPU sequential code, we guide the audience through the different steps that allowed us to increase performances on a GPU around 149 times the original runtime of the code (performances evaluated on a K20Xm). The same optimization strategy is applied to the CPU code and increases performances around 35 times the original run time (performances evaluated on a E5-1650v3 processor). Based on this methodology, we finally end up with an optimized unified version of the code which can run simultaneously on both GPU and CPU architectures.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Computational Fluid Dynamics, HPC and AI, GTC Europe 2017 - ID 23191
Download:
 
Flavors: Library for Fast Parallel Lookup Using Custom Radix Trees
Albert Wolant (WARSAW UNIVERSITY OF THECHNOLOGY)
Learn how to use configurable radix trees to perform fast parallel lookup operations on GPU. In this session you will find out how to use our library to create radix tree specifically tailored to your needs. You will also see examples on how to ...Read More

Learn how to use configurable radix trees to perform fast parallel lookup operations on GPU. In this session you will find out how to use our library to create radix tree specifically tailored to your needs. You will also see examples on how to squeeze the most performance out of presented data structures in real world applications. We will also show our results on using Deep Learning as a tool to customize data structures.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Tools and Libraries, GTC Europe 2017 - ID 23269
Download:
 
Welcome to the Jet Age – How AI and Deep Learning Make Online Shopping Smarter at Walmart
Daniel EGLOFF (QUANTALEA AG)
Online shopping is nothing if not efficient. Walmart together with new Jersey-startup Jet take things a step further, using AI and Deep Learning to optimize their entire E-Commerce business. The first AI application we discuss is Jet’s uni ...Read More

Online shopping is nothing if not efficient. Walmart together with new Jersey-startup Jet take things a step further, using AI and Deep Learning to optimize their entire E-Commerce business. The first AI application we discuss is Jet’s unique smart merchant selection: the platform finds the best merchant and warehouse combination in real time so that the total order cost is as low as possible. Then we show how to efficiently pack fresh and frozen orders with Deep Reinforcement Learning. The value of this approach is not just to find the best boxes and the tightest packing, but also the least amount of coolant and its placement so that the temperature of all items stays within the required limits during shipment.  

  Back
 
Keywords:
Algorithms and Numerical Techniques, Other, HPC and AI, GTC Europe 2017 - ID 23145
Download:
 
Accelerating Robust Normal Calculation on GPUs
Rohit Gupta (HERE GLOBAL B.V.)
Calculation of surface normals can be crucial to the process of extracting useful information from point clouds. Surface normals give an estimate of the objects in te scene which might be of importance for more complex algorithms like feature ex ...Read More

Calculation of surface normals can be crucial to the process of extracting useful information from point clouds. Surface normals give an estimate of the objects in te scene which might be of importance for more complex algorithms like feature extraction using machine learning techniques. In this poster, we present our implementation of normal estimation on a GPU and CPU and show results for both platforms. Through our implementation we show that GPU impementations can be up to an order of magnitude faster or more on a rather modest desktop Xeon workstation when compared to a GPU implementation on a Quadro M4000 graphics card. To substantiate our finding we also share profilign information and plots on the distribution of errors in our approach.

  Back
 
Keywords:
Algorithms and Numerical Techniques, HD Mapping, HPC and AI, GTC Europe 2017 - ID P23018
Download:
 
The Digital Transformation and How AI Reinvents Mobility
Johann JUNGWIRTH (VOLKSWAGEN AG)
Johann Jungwirth (JJ) provides his insights about the digital transformation of the automotive industry. He describes how automotive companies transform from hardware companies to hardware, software, and services companies. Furthermore, he highl ...Read More

Johann Jungwirth (JJ) provides his insights about the digital transformation of the automotive industry. He describes how automotive companies transform from hardware companies to hardware, software, and services companies. Furthermore, he highlights the increasing capabilities of AI technologies and how they will lead to the reinvention of the automotive industry, e.g. through the realization of self-driving-cars and customer-centered mobility services.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Self-Driving Cars, Other, GTC Europe 2017 - ID 23128
Download:
 
How to Optimise Sensor Fusion Algorithms into a PX2 Prototype
Felix EBERLI (SUPERCOMPUTING SYSTEMS AG), Stefan Hegemann (CONTINENTAL)
This session will describe how Supercomputing Systems AG addresses the key challenges when optimizing software runtime for self-driving vehicles. Our automotive Tier1 customer has developed the algorithms in C++ on a standard PC. The goal was to ...Read More

This session will describe how Supercomputing Systems AG addresses the key challenges when optimizing software runtime for self-driving vehicles. Our automotive Tier1 customer has developed the algorithms in C++ on a standard PC. The goal was to build a prototype on the PX2 Platform. In a first step, we profiled the algorithms on PC and PX2 and then started our optimizations on ARM and DENVER cores. As a further optimization, we will offload one of the algorithms to GPU.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Embedded & Robotics, Self-Driving Cars, GTC Europe 2017 - ID 23150
Download:
 
Fundamental AI Research: On Probabilistic Inference, Control, and Open-Sourcing
Patrick VAN DER SMAGT (VOLKSWAGEN AG)
Patrick van der Smagt will introduce the open-source AI research model at the Volkswagen Data Lab in Munich. Then he will present the winners of the 2017 VW-NVIDIA Deep Learning and Robotics Challenge. The winning team of this challenge, which b ...Read More

Patrick van der Smagt will introduce the open-source AI research model at the Volkswagen Data Lab in Munich. Then he will present the winners of the 2017 VW-NVIDIA Deep Learning and Robotics Challenge. The winning team of this challenge, which best solved a robotics challenge using deep neural networks, will be able to present their solution. Finally, the winners of Jugend Innovativ, Austria''s national science competition, will be presented.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Education and Training, Other, GTC Europe 2017 - ID 23335
Download:
 
GPU powered trajectory planning for autonomous driving
Jörg Küfen (FKA AACHEN), Marius STÄRK (INSTITUT FÜR KRAFTFAHRZEUGE - RWTH AACHEN UNIVERSITY)
This session will describe the potentials of a GPU based trajectory planner and its current development and integration level. Special attention will be paid to the operating principle, which includes a interaction of CPU and GPU on DRIVE PX 2. A be ...Read More
This session will describe the potentials of a GPU based trajectory planner and its current development and integration level. Special attention will be paid to the operating principle, which includes a interaction of CPU and GPU on DRIVE PX 2. A benchmark analysis on the load share of CPU and GPU, the resulting planning times and a concept for further performance enhancements will be showcased The presentation will also highlight the achievable planning performance with human capabilities and reaction time.  Back
 
Keywords:
Algorithms and Numerical Techniques, Performance Optimization, Self-Driving Cars, GTC Europe 2017 - ID 23351
Download:
 
Bridging the Gap: From Fundamental AI Research to Real-World Challenges
Yasser Jadidi (ROBERT BOSCH GMBH)
In this talk, we will give insights into the industrial challenges in automotive powertrain and autonomous driving perception. ...Read More

In this talk, we will give insights into the industrial challenges in automotive powertrain and autonomous driving perception.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Intelligent Machines and IoT, Computer Vision and Machine Vision, GTC Europe 2017 - ID 23355
Download:
 
Deep Learning Without Limits: NVIDIA GPU Cloud (NGC)
Jim McHugh (NVIDIA)
As deep learning initiatives become more prevalent, the need for critical GPU compute resources increases. NVIDIA DGX systems ushered in a new era of accelerated computing for deep learning, and the new NVIDIA GPU Cloud (NGC) extends these capabiliti ...Read More
As deep learning initiatives become more prevalent, the need for critical GPU compute resources increases. NVIDIA DGX systems ushered in a new era of accelerated computing for deep learning, and the new NVIDIA GPU Cloud (NGC) extends these capabilities with cloud-based GPU-accelerated environments that fully interoperate with DGX systems or PCs with NVIDIA TITAN Xp and GeForce GTX 1080 Ti graphics cards. Learn how to use NGC to optimize deep learning workflows with GPU-accelerated cloud computing environments, how to use the NGC Container Registry, and how to leverage unified job scheduling across cloud and on-premises systems, helping you solve the most complex AI challenges. As a session attendee, you will be given exclusive access to the NGC private beta to try it for yourself.  Back
 
Keywords:
Algorithms and Numerical Techniques, Data Center and Cloud Infrastructure, Tools and Libraries, GTC Europe 2017 - ID 23387
 
Towards Green Aviation with Python at Petascale
Peter Vincent (IMPERIAL COLLEGE LONDON)
Accurate simulation of unsteady turbulent flow is critical for improved design of greener aircraft that are more fuel-efficient. We will demonstrate the application of PyFR to petascale simulation of such flows. Rationale behind algorithmic choi ...Read More

Accurate simulation of unsteady turbulent flow is critical for improved design of greener aircraft that are more fuel-efficient. We will demonstrate the application of PyFR to petascale simulation of such flows. Rationale behind algorithmic choices, which offer increased levels of accuracy and enable sustained computation at up to 58% of peak DP-FLOPs on unstructured grids, will be discussed. A range of software innovations will also be detailed, including use of runtime code generation, which enables PyFR to efficiently target multiple platforms via a single implementation. Finally, results will be presented from fullscale simulations of flow over low-pressure turbine blades, along with scaling results, and performance data demonstrating sustained computation at up to 13.7 DP-PFLOPs.

  Back
 
Keywords:
Algorithms and Numerical Techniques, In-Situ and Scientific Visualization, Computational Fluid Dynamics, GTC Europe 2017 - ID 23430
Download:
 
How To Make A Embedded Product From Your PC Developed Algorithm
Cyril RUSSO (NEXVISION)
A description of the process to make a tangible industrial product from lab developed algorithms This speech is based on a real world example, and explain the common pitfalls and caveats, the process used and the strategies to fit large GPU algo ...Read More

A description of the process to make a tangible industrial product from lab developed algorithms This speech is based on a real world example, and explain the common pitfalls and caveats, the process used and the strategies to fit large GPU algorithms on an embedded GPU while maintaining acceptable performance and latencies.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Embedded & Robotics, Computer Vision and Machine Vision, GTC Europe 2017 - ID 23436
Download:
 
Camera based Lane Detection using a Deep Learning Approach
Asad Ismail (VISTEON ELECTRONICS)
There has been an explosion of research for camera based lane detection using deep learning approaches. We would like to present our model of Lane Detection which uses a blend of conventional and deep learning based approach. This has been teste ...Read More

There has been an explosion of research for camera based lane detection using deep learning approaches. We would like to present our model of Lane Detection which uses a blend of conventional and deep learning based approach. This has been tested in real life automotive use case and we would like to provide snapshots of the results so far.

  Back
 
Keywords:
Algorithms and Numerical Techniques, Self-Driving Cars, Computer Vision and Machine Vision, GTC Europe 2017 - ID 23437
Download:
 
A Deep Learning Approach for Pose Estimation.
Kanter VAN DEURZEN (DELFT ROBOTICS)
This session will cover several approaches with which full 6-DOF pose estimation can be achieved based on deep learning. In order to singulate objects from a chaotic environment, robotics often requires the estimation of the pose of an object. Exampl ...Read More
This session will cover several approaches with which full 6-DOF pose estimation can be achieved based on deep learning. In order to singulate objects from a chaotic environment, robotics often requires the estimation of the pose of an object. Example applications are bin-picking, machine tending and order-picking. Conventional techniques rely on computationally intensive algorithms, additionally they are ill-suited for quick re-implementation on new objects. Although some academic research has explored the value of a deep learning approach for this purpose, no robust design is available as of yet. During this talk we discuss three different approaches to achieve rough but correct pose estimation directly from a neural network.  Back
 
Keywords:
Algorithms and Numerical Techniques, Embedded & Robotics, Computer Vision and Machine Vision, GTC Europe 2017 - ID 23444
Download:
Astronomy and Astrophysics
Presentation
Media
Energy Efficient Real-Time Computing for Extremely Large Telescopes with DGX-1
Damien GRATADOUR (OBSERVATOIRE DE PARIS)
Come and learn how the grand challenge of controlling adaptive optics systems on future Extremely Large Telescopes is being solved using GPUs. As part of Green Flash, an international EU funded joint industrial and academic project, our team is ...Read More

Come and learn how the grand challenge of controlling adaptive optics systems on future Extremely Large Telescopes is being solved using GPUs. As part of Green Flash, an international EU funded joint industrial and academic project, our team is developing solutions based on GPUs for the real-time control of large optical systems operating under tough operating environments. This includes the hard real-time data pipeline, the soft real-time supervisor module as well as a real-time capable numerical simulation to test and verify the proposed solutions. We will discuss how the unprecedented memory bandwidth provided by HBM2 on the new Pascal architecture is changing the game in dimensioning these complex real-time computers crunching up to 200 Gb/s of noisy data.

  Back
 
Keywords:
Astronomy and Astrophysics, Computer Vision and Machine Vision, HPC and AI, GTC Europe 2017 - ID 23171
Download:
 
Heterogeneous Event Selection at the CMS experiment
Felice Pantaleo (CERN)
Starting from 2020, during the Large Hadron Collider Runs 3 and 4, the increased accelerator luminosity with the consequently increased number of simultaneous proton-proton collisions (pile-up) will pose significant new challenges for the CMS ex ...Read More

Starting from 2020, during the Large Hadron Collider Runs 3 and 4, the increased accelerator luminosity with the consequently increased number of simultaneous proton-proton collisions (pile-up) will pose significant new challenges for the CMS experiment. A many-threads-per-event approach would scale with the pileup, by offloading the combinatorics to the number of threads available on the GPU. This would allow a faster execution of track reconstruction and physics selection algorithms in charge of accepting the events with the most interesting physics content.

  Back
 
Keywords:
Astronomy and Astrophysics, Computational Physics, GTC Europe 2017 - ID 23232
Download:
Computational Biology and Chemistry
Presentation
Media
Protein Biophysics from Machine Learning and AI perspective
Kamil Tamiola (PEPTONE - THE PROTEIN INTELLIGENCE COMPANY)
An overwhelming amount of experimental evidence suggests that elucidations of protein function, interactions, and pathology are incomplete without inclusion of intrinsic protein disorder and structural dynamics. Thus, to expand our understanding ...Read More

An overwhelming amount of experimental evidence suggests that elucidations of protein function, interactions, and pathology are incomplete without inclusion of intrinsic protein disorder and structural dynamics. Thus, to expand our understanding of intrinsic protein disorder and provide Machine Learning and AI solutions for biotechnology, we have created a database of secondary structure  propensities for proteins (dSPP) as a reference resource for experimental research and computational biophysics. Database of Structural Propensities of Proteins (dSPP) is the world’s first interactive repository of structural and dynamic features of proteins with seamless integration for leading Machine Learning frameworks, Keras and Tensorflow.

  Back
 
Keywords:
Computational Biology and Chemistry, Computational Physics, GTC Europe 2017 - ID 23058
Download:
 
Personalizing Medicine and Healthcare using GPUs, Decision Support and Smart IoT
Steve Gardner (ROWANALYTICS LTD)
This talk presents a groundbreaking multi-factor genomic, phenotypic & clinical data association platform and its use in building accurate disease risk models and clinical decision support tools. ...Read More

This talk presents a groundbreaking multi-factor genomic, phenotypic & clinical data association platform and its use in building accurate disease risk models and clinical decision support tools.

  Back
 
Keywords:
Computational Biology and Chemistry, Intelligent Machines and IoT, HPC and AI, GTC Europe 2017 - ID 23018
Download:
 
Learn how one the #1 Aviation Equipment supplier provides its engineers with a solution that allows them to work wherever the need to and collaborate in real time. They implemented a centralized and virtualized environment to deliver a secure, f ...Read More

Learn how one the #1 Aviation Equipment supplier provides its engineers with a solution that allows them to work wherever the need to and collaborate in real time. They implemented a centralized and virtualized environment to deliver a secure, flexible and scalable VDI solution to provide them access to their tools like Solidworks, SmarTeams and Catia with a better than local User experience for engineers around the world.

  Back
 
Keywords:
Computational Biology and Chemistry, GTC Europe 2017 - ID 23056
Download:
 
BrianQC module for Q-Chem 5.0: GPU-cloud based, high angular momentum integrator
Quantum chemical calculations with chemically satisfying precision and feasible computation time is still not entirely solved. To solve this we propose a compiler technology based solution for NVIDIA GPU’s. The two electron integral calcul ...Read More

Quantum chemical calculations with chemically satisfying precision and feasible computation time is still not entirely solved. To solve this we propose a compiler technology based solution for NVIDIA GPU’s. The two electron integral calculation problem can be carried out in a large number of ways. The optimal approach varies for each integral type. Our machine learning based algorithm chooses the best integral paths for a given type. Based on this technology we managed to reach the lowest computation time for a given task with given precision.

  Back
 
Keywords:
Computational Biology and Chemistry, GTC Europe 2017 - ID P23056
 
Using Cloud-based Deep Learning AI Platform to Analyze Gigantic Pathology Images
Kaisa Helminen (FIMMIC)
Well introduce a novel approach to digital pathology analytics, which brings together a powerful image server and deep learning-based image analysis on a cloud platform. Recent advances in artificial intelligence (AI) and deep learning in partic ...Read More

Well introduce a novel approach to digital pathology analytics, which brings together a powerful image server and deep learning-based image analysis on a cloud platform. Recent advances in artificial intelligence (AI) and deep learning in particular show great promise in several fields of medicine, including pathology. Human expert judgment, augmented by deep learning algorithms, has the potential to speed up the diagnostic process and to make diagnostic assessments more reproducible. We will present examples on context-intelligent image analysis applications, including e.g. fully automated epithelial cell proliferation assay and tumor grading. We will also present other examples of complex image analysis algorithms, which all run on-demand on our WebMicroscope® Cloud environment.

  Back
 
Keywords:
Computational Biology and Chemistry, Computer Vision and Machine Vision, Medical Imaging and Radiology, GTC Europe 2017 - ID 23275
Download:
 
Developing a deep learning and AI platform for life science research
Robert ESNOUF (WCHG/BDI UNIVERSITY OF OXFORD)
The WCHG and BDI at the University of Oxford have an established research computing platform for genomics, statistical genetics and structural biology research and I will outline how we are developing this platform to include a significant GPU i ...Read More

The WCHG and BDI at the University of Oxford have an established research computing platform for genomics, statistical genetics and structural biology research and I will outline how we are developing this platform to include a significant GPU infrastructure to support our researchers great wave of enthusiasm for exploring the potential of deep learning and AI for life sciences research. We are deploying a mixture of GPU architectures and deep learning AI frameworks and I will report on our current plans the the initial areas of research in the life sciences that show promise for AI.

  Back
 
Keywords:
Computational Biology and Chemistry, HPC and AI, GTC Europe 2017 - ID 23451
Download:
Computational Fluid Dynamics
Presentation
Media
GPU-based CFD for Ultra-fast, High-fidelity Simulations for Automotive Aerodynamics
Christian Janßen (TUHH-ALTAIR)
Learn how GPU-based Computational Fluid Dynamics (CFD) paves the way for affordable high-fidelity simulations of automotive aerodynamics. Highly-resolved, transient CFD simulations based on pure CPU systems are computationally expensive and cons ...Read More

Learn how GPU-based Computational Fluid Dynamics (CFD) paves the way for affordable high-fidelity simulations of automotive aerodynamics. Highly-resolved, transient CFD simulations based on pure CPU systems are computationally expensive and constrained by available computational resources. This was posing a big challenge for automotive OEMs in their aerodynamic design process over many years. To overcome this problem, we present ultraFluidX, a novel CFD solver that was specifically designed to leverage the massively parallel architecture of GPUs. With its multi-GPU implementation based on CUDA-aware MPI, the tool can achieve turnaround times of just a few hours for simulations of fully detailed production-level passenger and heavy-duty vehicles a breakthrough for simulation-based design.

  Back
 
Keywords:
Computational Fluid Dynamics, HPC and AI, GTC Europe 2017 - ID 23327
Download:
 
High Resolution GPU Codes for Direct Numerical Simulation of Turbulence
Alberto Vela-Martin (TECHNICAL UNIVERSITY OF MADRID)
New high order, high resolution hybrid MPI-CUDA codes for the simulation of turbulent flows on many distributed GPUs will be presented. ...Read More

New high order, high resolution hybrid MPI-CUDA codes for the simulation of turbulent flows on many distributed GPUs will be presented.

  Back
 
Keywords:
Computational Fluid Dynamics, HPC and AI, GTC Europe 2017 - ID 23179
Download:
 
First Steps of YALES2 Code Towards GPU Acceleration on Standard and Prototype Cluster
Jean-Matthieu ETANCELIN (UNIVERSITY OF REIMS / ROMEO HPC CENTER), Arnaud Renard (UNIVERSITY OF REIMS CHAMPAGNE-ARDENNE - ROMEO HPC CENTER)
Learn how we explore the feasibility of porting YALES2 on GPU. YALES2 is an HPC application for turbulent combustion modeling from primary atomization to pollutant prediction on massive complex meshes. It runs over thousands of CPU cores solving seve ...Read More
Learn how we explore the feasibility of porting YALES2 on GPU. YALES2 is an HPC application for turbulent combustion modeling from primary atomization to pollutant prediction on massive complex meshes. It runs over thousands of CPU cores solving several billions element meshes through MPI+OpenMP programming. The work presented here is focusing on a preliminary feasibility study of GPU porting. In this session we will describe: a methodology for porting a large code to GPU; the choices that have been made regarding the different constraints; the performance results. We will also present the final benchmarks run across several platforms form classic Intel+Kepler cluster at ROMEO HPC Center (University of Reims, France) to prototypes with IBM Power8+Pascal at IDRIS (CNRS, France).  Back
 
Keywords:
Computational Fluid Dynamics, HPC and AI, GTC Europe 2017 - ID 23254
Download:
 
How to Prepare Weather and Climate Models for Future HPC Hardware
Peter DUEBEN (EUROPEAN WEATHER CENTRE (ECMWF))
Learn how one of the leading institutes for global weather predictions, the European Centre for Medium-Range Weather Forecasts (ECMWF), is preparing for exascale supercomputing and the efficient use of future HPC computing hardware. I will name ...Read More

Learn how one of the leading institutes for global weather predictions, the European Centre for Medium-Range Weather Forecasts (ECMWF), is preparing for exascale supercomputing and the efficient use of future HPC computing hardware. I will name the main reasons why it is difficult to design efficient weather and climate models and provide an overview on the ongoing community effort to achieve the best possible model performance on existing and future HPC architectures. I will present the EU H2020 projects ESCAPE and ESiWACE and discuss recent approaches to increase computing performance in weather and climate modelling such as the use of reduced numerical precision and deep learning.

  Back
 
Keywords:
Computational Fluid Dynamics, HPC and AI, HPC and Supercomputing, GTC Europe 2017 - ID 23348
Download:
Computational Physics
Presentation
Media
Coupling of Model Hierarchies in Numerical Plasma Simulations on Hybrid GPU-CPU Systems
Simon LAUTENBACH (RUHR-UNIVERSITÄT BOCHUM)
We use a heterogeneous programming approach to couple kinetic and fluid plasma descriptions on hybrid GPU-CPU systems. Kinetic plasma descriptions are inherently expensive to solve. We adaptively couple Vlasov and much cheaper 10-moment multiflu ...Read More

We use a heterogeneous programming approach to couple kinetic and fluid plasma descriptions on hybrid GPU-CPU systems. Kinetic plasma descriptions are inherently expensive to solve. We adaptively couple Vlasov and much cheaper 10-moment multifluid codes. To achieve optimal performance, we use a heterogeneous approach: The easily parallelizable Vlasov equation is solved on GPUs, while the cheap multifluid and Maxwell codes, the work-balancing and communication are handled by CPUs.

  Back
 
Keywords:
Computational Physics, HPC and AI, GTC Europe 2017 - ID P23044
 
Scientific Ray-Tracing with OptiX
Timo Stich (ZEISS)
We present our findings on using the NVIDIA OptiX framework to simulate the scattering of electrons as encountered in scanning electron microscope environments. In particular, we discuss how we implemented volume scattering and coplanar material ...Read More

We present our findings on using the NVIDIA OptiX framework to simulate the scattering of electrons as encountered in scanning electron microscope environments. In particular, we discuss how we implemented volume scattering and coplanar material transition boundaries with varying material properties within the framework. The results have been verified with established CPU based simulation packages. While achieving comparable accuracy, significant speed ups are realized.

  Back
 
Keywords:
Computational Physics, Rendering and Ray Tracing, GTC Europe 2017 - ID 23136
Download:
 
NVIDIA Isaac: A Peek under the Hood
Adam Moravanszky (NVIDIA)
In this talk we share how Isaac Lab, our hyper-real training environment for real robots, went from idea to a fully functional proof of concept in just a few months. We showcase our dominoes playing robot Isaac who is a capable opponent in both Holod ...Read More
In this talk we share how Isaac Lab, our hyper-real training environment for real robots, went from idea to a fully functional proof of concept in just a few months. We showcase our dominoes playing robot Isaac who is a capable opponent in both Holodeck virtual reality as well as real life. An interdisciplinary team of engineers leveraged a broad range of tools to bridge the gap between virtual and reality to let robots learn faster than ever. We dive into a number of challenges in graphics, virtual reality, computer vision, physical simulation, and machine learning that had to be overcome to make Isaac a viable solution end to end.  Back
 
Keywords:
Computational Physics, Embedded & Robotics, Computer Vision and Machine Vision, GTC Europe 2017 - ID 23386
Download:
Computer Aided Engineering
Presentation
Media
From Dream to Reality: High Performance 3D Graphics Desktop Virtualisation with NVIDIA GRID Technology
MEHMET TUNC (FNSS DEFENSE SYSTEMS)
A promising, exciting journey to enterprise 3D virtualisation. A long-awaited answer to the question: Is it possible for you to run your high-end-graphics engineering applications, such as CATIA and NX, in your enterprise data center and cloud? ...Read More

A promising, exciting journey to enterprise 3D virtualisation. A long-awaited answer to the question: Is it possible for you to run your high-end-graphics engineering applications, such as CATIA and NX, in your enterprise data center and cloud? Can virtual desktops provide the required performance, just like a powerful workstation? Delivering high performance remote workstations was technically inadequate, complicated and costly but now with NVIDIA GRID technology, the reply is absolutely YES! Join our session and hear our exciting journey for 3D Desktop virtualisation. Learn the details of our transition story to a successful extended live system; examine the provided values and technical considerations necessary to properly enable high performance 3D Desktops.

  Back
 
Keywords:
Computer Aided Engineering, Data Center and Cloud Infrastructure, Performance Optimization, GTC Europe 2017 - ID 23187
Download:
 
Use of Collaborative Design Review to involve remote offices
Keith Russell (VIRTALIS)
Virtalis and its customers will explain how its VR software is used for design review with a specific focus on collaboration with remote offices and workers in the field using hardware powered by NVidia technology. ...Read More

Virtalis and its customers will explain how its VR software is used for design review with a specific focus on collaboration with remote offices and workers in the field using hardware powered by NVidia technology.

  Back
 
Keywords:
Computer Aided Engineering, Large Scale and Multi-Display Visualization, Real-Time Graphics, GTC Europe 2017 - ID 23243
Download:
 
Visualisation with NVIDIA P6000
Niko Scrbak (SMW-AUTOBLOK SPANNSYSTEME GMBH)
In this session, we will discuss how to use Nvidia P6000 with Solid Works Visualize Professional as well as exploring the advantages of the new Nvidia P6000, time saving with the new VGA and results for the customer. ...Read More
In this session, we will discuss how to use Nvidia P6000 with Solid Works Visualize Professional as well as exploring the advantages of the new Nvidia P6000, time saving with the new VGA and results for the customer.  Back
 
Keywords:
Computer Aided Engineering, Rendering and Ray Tracing, Video and Image Processing, GTC Europe 2017 - ID 23098
 
GPU Driven Innovation at McLaren Technology Group
Michael ROSAM (MCLAREN)
GPUs are enabling innovation across automotive, motorsport, healthcare and transportation industries. McLaren will provide an overview of novel applications at both McLaren Automotive and McLaren Applied Technologies. ...Read More

GPUs are enabling innovation across automotive, motorsport, healthcare and transportation industries. McLaren will provide an overview of novel applications at both McLaren Automotive and McLaren Applied Technologies.

  Back
 
Keywords:
Computer Aided Engineering, Performance Optimization, Real-Time Graphics, GTC Europe 2017 - ID 23501
Download:
Computer Vision and Machine Vision
Presentation
Media
Real Time Path Tracing Using a Hybrid Deferred Approach
Francisco Jose Garcia (UNIVERSIDAD REY JUAN CARLOS)
We present an approach of using real time path tracing in combination with traditional deferred techniques. This method allows to use most elements of a traditional rendering pipeline (like direct light and post effects) and keep the BVH ray tra ...Read More

We present an approach of using real time path tracing in combination with traditional deferred techniques. This method allows to use most elements of a traditional rendering pipeline (like direct light and post effects) and keep the BVH ray traversal usage at a minimum. In combination with adaptive filtering, GPU data streaming and mesh preprocessing, this technique allows for real time frame rates up to Virtual Reality usage on a single GPU. The robust implementation is used for architectural visualization but can also be used at games and other areas with a wide range of direct and indirect lighting phenomena. We finally compare our results with our offline path tracer implementation.

  Back
 
Keywords:
Computer Vision and Machine Vision, Embedded & Robotics, GTC Europe 2017 - ID 23026
Download:
 
Dumpster Detector for Smart Cities
David Concha (UNIVERSIDAD REY JUAN CARLOS)
In this poster we present a convolutional network for the detection of dumpsters. Because our goal is to install a device embedded in a garbage truck to detect and locate the containers automatically, we need to reduce the computational cost of ...Read More

In this poster we present a convolutional network for the detection of dumpsters. Because our goal is to install a device embedded in a garbage truck to detect and locate the containers automatically, we need to reduce the computational cost of each network evaluation to be suitable for embedded devices. We modify the detection network by removing the maxpool layer and perform a study to see if the improvement of the execution time compensates for the loss of quality that it produces.

  Back
 
Keywords:
Computer Vision and Machine Vision, Embedded & Robotics, Video and Image Processing, GTC Europe 2017 - ID P23027
 
Achieving Fast, Accurate and Customized Visual Similarity Search on Real-world Images
Marko VELIC (STYRIA)
Dive deep into convolutional neural network layers and features and learn what is needed for a production-level image search system to be put in the hands of users. Poster will be based on real-world project - the Willhabens Fashion Cam. Poster ...Read More

Dive deep into convolutional neural network layers and features and learn what is needed for a production-level image search system to be put in the hands of users. Poster will be based on real-world project - the Willhabens Fashion Cam. Poster will present technical details of the system including machine learning training details, CNNs dissecting and tweaking but also production level serving details and GPU-powered infrastructure challenges and solutions. We will show how product evolved over time based on users feedback and how data scientists responded by tweaking CNNs in the right way. Additionally, details of combining textual information along with images to identify brands even if no pixel-level or bounding box annotations are present in the training data, will be presented.

  Back
 
Keywords:
Computer Vision and Machine Vision, Signal and Audio Processing, Video and Image Processing, GTC Europe 2017 - ID P23037
 
Tracking single immune cell for 24h: Real-time intravital study with GPU acceleration
Mykhailo VLADYMYROV (LHEP, UNIVERSITY OF BERN)
Only 1 in 10^6 T cells, providing us with everyday immune defense, is sensitive to a particular antigen, which complicates studies of rare interactions of a particular cell type. These studies have advanced with the development of intravital dee ...Read More

Only 1 in 10^6 T cells, providing us with everyday immune defense, is sensitive to a particular antigen, which complicates studies of rare interactions of a particular cell type. These studies have advanced with the development of intravital deep-tissue imaging. However, long-term imaging and tracking of single cells have been a long-standing challenge particularly because of tissue drift caused by vital activity. Here, we present a system that, exploiting GPU computing, enables prolonged imaging and increases the fraction of successful datasets by a factor of 5, contributing to sustainable biological research. Currently, we are implementing a real-time immune cell tracking and behavior analysis system for rare immune cell interaction study, which also heavily relies on the use of GPUs.

  Back
 
Keywords:
Computer Vision and Machine Vision, HPC and AI, Medical Imaging and Radiology, GTC Europe 2017 - ID P23050
 
Smart Traffic Lights for Dynamic Bicycle Green Waves
Edward Zimmermann (NONMONOTONIC NETWORKS)
Instead of static ""green wave"" timings or priorities, a work in progress system is presented that learns to increase the flow of bicycle traffic while minimizing the impact on other traffic actors. The system considers not ...Read More

Instead of static ""green wave"" timings or priorities, a work in progress system is presented that learns to increase the flow of bicycle traffic while minimizing the impact on other traffic actors. The system considers not just the flow in the bike lane but also traffic conditions, rain. others traffic actors in the lane (such as delivery vehicles and pedestrians) and mass transport movements (TSP). Using low power efficient SoCs -- Tegra X1 -- the ""smarts"" are integrated in traffic lights and provide V2I interfaces -- also to mobile phones of cyclists -- about signal changes and warn of pedestrians or cyclists. Using image based object recognition it dispenses with the need for sensors buried in the pavement making the system not just smarter but also comparatively inexpensive.

  Back
 
Keywords:
Computer Vision and Machine Vision, Embedded & Robotics, Intelligent Machines and IoT, GTC Europe 2017 - ID P23052
 
Distanceless Label Propagation: a GPU-optimized Direct Connected Component Labeling Algorithm
Lionel LACASSAGNE (LIP6 (LABORATOIRE D'INFORMATIQUE DE PARIE 6))
We present a new Connected Component Labeling algorithm for GPU named DLP (Distanceless Label Propagation). DLP deeply takes into account the architectural properties of the GPU to be efficient. Thanks to a recursive union-find with atomic instr ...Read More

We present a new Connected Component Labeling algorithm for GPU named DLP (Distanceless Label Propagation). DLP deeply takes into account the architectural properties of the GPU to be efficient. Thanks to a recursive union-find with atomic instructions, DLP is no more iterative like many algorithms for GPUs, but direct like the algorithms for multi-core processors. Moreover, a pre-processing step is used to speedup the border merging. An exhaustive benchmark on Jetson TK1, TX1 and TX2 shows that DLP performs well whatever the nature of the image is - even on random images - and thus is more efficient than existing CCL algorithms for GPU.

  Back
 
Keywords:
Computer Vision and Machine Vision, Embedded & Robotics, Performance Optimization, GTC Europe 2017 - ID P23061
 
How to Get Regulatory Approval for an AI-based Autonomous Car?
Alex Haag (AUTONOMOUS INTELLIGENT DRIVING GMBH)
Proving that such a complex system as an autonomous car is safe cannot be done using existing standards.   A new method needs to be invented that is much more data driven and probability based. Traditional redundant   solutio ...Read More

Proving that such a complex system as an autonomous car is safe cannot be done using existing standards.   A new method needs to be invented that is much more data driven and probability based. Traditional redundant   solutions don't apply when trying to optimize a Precision-Recall curve. Getting acceptance from the regulatory bodies and the public will be much easier if the industry converges on what this new method shall be.

  Back
 
Keywords:
Computer Vision and Machine Vision, Self-Driving Cars, Computer Vision and Machine Vision, GTC Europe 2017 - ID 23166
 
Large-scale Mapping with Street-level Images
Yubin KUANG (MAPILLARY)
Well discuss the challenges in creating maps from hundreds of millions of street-level images and the solutions we have developed using deep learning and computer vision techniques. Map creation is one of the essential problems for autonomous dr ...Read More

Well discuss the challenges in creating maps from hundreds of millions of street-level images and the solutions we have developed using deep learning and computer vision techniques. Map creation is one of the essential problems for autonomous driving. The two essential components for map creation are object recognition and 3D reconstruction. Well discuss how we increase our object recognition capacity by combining the deep learning techniques weve developed and the Mapillary Vistas Dataset (the worlds largest street-level dataset with instance-aware segmentation). Well also look into the challenges in large-scale 3D reconstruction including scalability, semantic understanding integration, and camera self-calibration. Finally, we will demonstrate the map data that we generate.

  Back
 
Keywords:
Computer Vision and Machine Vision, HD Mapping, Self-Driving Cars, GTC Europe 2017 - ID 23330
Download:
 
Teaching Cars, Robots and Buildings to Read Human Body Language using Webcams and GPUs
Paul Kruszewski (WRNCH)
As AI makes the connected world of cars, robots and buildings more and more intelligent, it is becoming increasingly important for these intelligent entities to interact with humans in natural ways. Human beings are highly visual creatures for w ...Read More

As AI makes the connected world of cars, robots and buildings more and more intelligent, it is becoming increasingly important for these intelligent entities to interact with humans in natural ways. Human beings are highly visual creatures for whom 80% of communication is non-verbal. In this talk, we present a computer vision AI technology that allows humans to interact naturally with intelligent machines by giving the machines the ability to see and understand human intent. We provide a brief overview of how to apply GPU-based deep learning techniques to extract 3D human motion data capture from standard 2D RGB video. We'll describe in detail the stages of our NVIDIA® CUDA®-based pipeline, from training on DGX-1s to edge-based deployment on Jetson TX2s.

  Back
 
Keywords:
Computer Vision and Machine Vision, Embedded & Robotics, GTC Europe 2017 - ID 23375
Download:
 
Deep Learning & TensorRT Powered Video Analytics and Future of Intelligent Sports Sponsorship
Mike KEMELMAKHER (SAP SE)
Global sponsorship budgets in 2016 reached US$60B, with media production companies generating hundreds thousands hours of sports related video content on an annual basis. Investments in sponsoring of sports events is now critical for many brands, so ...Read More
Global sponsorship budgets in 2016 reached US$60B, with media production companies generating hundreds thousands hours of sports related video content on an annual basis. Investments in sponsoring of sports events is now critical for many brands, so how can this spend be measured and optimized ? This session looks at where we are now with SAP Brand Impact solution: how we can accurately measure the exposure of brand visual assets seen on TV using Deep Learning and Computer Vision. We will share our recent experience with Volta GPUs and TensorRT3, and what the impact is on our solution performance.  Back
 
Keywords:
Computer Vision and Machine Vision, Intelligent Video Analytics and Smart Cities, Media and Entertainment, GTC Europe 2017 - ID 23503
 
Lessons Learned in a Large-Scale Facial and Environment Recognition System Using Clustered DGX Systems
Harris Hall (PURE STORAGE)
Image recognition identifies one or more people in images or videos by analyzing and comparing patterns. Algorithms for face recognition typically extract facial features and compare them to a database to find the best match. This system may be used ...Read More
Image recognition identifies one or more people in images or videos by analyzing and comparing patterns. Algorithms for face recognition typically extract facial features and compare them to a database to find the best match. This system may be used in biometric, security, and surveillance systems, but is also useful in the social media space where personal affinities can be applied upon successful identification. The infrastructure to support the training and building phases of this application requires a large amount of data to be processed in parallel.  Back
 
Keywords:
Computer Vision and Machine Vision, Intelligent Video Analytics and Smart Cities, Video and Image Processing, GTC Europe 2017 - ID 23070
Download:
 
Smarter Humanoid Companion - Embedded GPUs can Make Your Robotic Companion More Alive
Alexandre Mazel (SOFTBANK ROBOTICS EUROPE)
Learn how our world can be understood better and faster by our robotic companions thanks to embedded GPUs. Our current advances in embedding the JetsonTX2 into Softbanks Pepper, the worlds leading affordable humanoid robot, shows that along with ...Read More

Learn how our world can be understood better and faster by our robotic companions thanks to embedded GPUs. Our current advances in embedding the JetsonTX2 into Softbanks Pepper, the worlds leading affordable humanoid robot, shows that along with the newly gained autonomy, confidentiality issues are also addressed due to embedded processing power. As no personal data needs to be processed on the cloud, your home privacy is maintained. This enhanced solution that we will present helps the robot to navigate better, recognize more objects quicker and allows it to interact fluidly with humans. A live demo of the autonomous Pepper Robot embedding the Jetson TX2 and navigating and interacting on stage will be done during the session.

  Back
 
Keywords:
Computer Vision and Machine Vision, Embedded & Robotics, GTC Europe 2017 - ID 23088
Download:
 
Using Deep Learning to Capture Storytelling in Photography
Appu Shaji (EYEEM)
Explore how researchers are using deep learning to uncover stories hidden in photos while connecting them to audiences. With the rise of mobile cameras, the process of capturing good photos has been democratized - and this overload of content ha ...Read More

Explore how researchers are using deep learning to uncover stories hidden in photos while connecting them to audiences. With the rise of mobile cameras, the process of capturing good photos has been democratized - and this overload of content has created a challenge in search. One of the important aspects of photography is that every image communicates with a different audience in different form. The goal of good search and discovery is to connect a target audience with stories that resonate with them. Deep Learning models encode rich representations about photographs. In this talk I will explain how our researchers use various combination of machine learning driven techniques that help understand various subtleties in photographic data, and match it with a target audience.

  Back
 
Keywords:
Computer Vision and Machine Vision, Video and Image Processing, GTC Europe 2017 - ID 23092
Download:
 
Yandex Autonomous Vehicle: Achievements and Challenges in Environment Perception
Anton Slesarev (YANDEX), Fedor CHERVINSKY (YANDEX)
Perception is a key component of self-driving technology. The better a car understands its environment, the more reliable the decision-making car control system will be. This session will provide an overview of the key sensor processing and fusi ...Read More

Perception is a key component of self-driving technology. The better a car understands its environment, the more reliable the decision-making car control system will be. This session will provide an overview of the key sensor processing and fusion algorithms required for autonomous vehicles, and discuss the challenges on the way towards Level 5 self-driving. Specifically, we address the challenge of processing huge amounts of data from all vehicle sensors in real-time, while achieving good results on public and private benchmarks.

  Back
 
Keywords:
Computer Vision and Machine Vision, HD Mapping, Self-Driving Cars, GTC Europe 2017 - ID 23094
Download:
 
Light Fields Pipeline for Immersive Video Experiences
VALERIE ALLIE (TECHNICOLOR)
Immersive Experiences require a sense of depth and freedom when navigating through the content. CG Light Field content applied to VR delivers such an immersive experience, with Light Field video capture even enabling the introduction of real content. ...Read More
Immersive Experiences require a sense of depth and freedom when navigating through the content. CG Light Field content applied to VR delivers such an immersive experience, with Light Field video capture even enabling the introduction of real content. From a Light Field capture of any time and of any scene, a description of the scene is given in a form of a dense point cloud associated with scale information. In this talk, Valerie Allie will present Technicolor's capture setup and the associated content pre-processing pipeline. Complementary use cases will also be demonstrated for photogrammetry and volumetric capture systems. Each pipeline module will be described with regards to the required architecture to process, create and render the associated dense point cloud.  Back
 
Keywords:
Computer Vision and Machine Vision, Media and Entertainment, Video and Image Processing, GTC Europe 2017 - ID 23102
Download:
 
Deep Learning for Complexity and Capability in Humanoid Robots
Rob Knight (THE ROBOT STUDIO), Cyril JOURDAN (THE ROBOT STUDIO)
In a post robot-revolution world we imagine a shiny army of willing workers and boundless leisure time with free dental for all - in reality, getting a robot to do simple household tasks is still beyond us. Why are humanoid robots so hard to bui ...Read More

In a post robot-revolution world we imagine a shiny army of willing workers and boundless leisure time with free dental for all - in reality, getting a robot to do simple household tasks is still beyond us. Why are humanoid robots so hard to build and control and what can be done to fully take advantage of the wealth of new AI tools available? We view the robot as an advanced power tool that can perform a wide range of tasks using only human tools and adaptable software to the extent that from the users point of view the task could be accomplished entirely by the robot a robot is not an appliance. Such a machine is necessarily complicated and the great promise of GPUs and DL is that we can finally control robots that approach the mechanical capabilities of the human body.

  Back
 
Keywords:
Computer Vision and Machine Vision, Embedded & Robotics, Intelligent Machines and IoT, GTC Europe 2017 - ID 23133
Download:
 
Park Smart AISee: AI at the Edge to Solve Parking Problem
Marco Moltisanti (PARK SMART S.R.L.)
Park Smart is a solution to lead drivers to find free parking spaces, and help parking owners and managers to improve their business. We exploit the paradigm of Edge Computing, moving the computational load from servers in the Cloud to embedded ...Read More

Park Smart is a solution to lead drivers to find free parking spaces, and help parking owners and managers to improve their business. We exploit the paradigm of Edge Computing, moving the computational load from servers in the Cloud to embedded devices located in place. Such a solution dramatically reduces the bandwidth consumption by ~95%. We perform the fine-tuning of a pre-trained CNN model able to classify empty vs. non empty parking lots using the NVIDIA Jetson inside our AISee box, and then we stream the result to the Cloud as a JSON file. A DL pipeline allows us to have a more robust classification with respect to classical CV techniques. We will present our end-to-end architecture together with the results of the benchmark tests about fine-tuning and classification on TXn.

  Back
 
Keywords:
Computer Vision and Machine Vision, Embedded & Robotics, Intelligent Machines and IoT, GTC Europe 2017 - ID 23139
Download:
 
Tegra Goes Industry: Embedded Hyperspectral Imaging
Michael Schoeffmann (PERCEPTION PARK GMBH)
Color the invisible: This is the potential of hyperspectral imaging. We will dive into the key concepts of molecular spectroscopy and will uncover the hidden treasures this amazing new technology offers to industry. The application in real world ...Read More

Color the invisible: This is the potential of hyperspectral imaging. We will dive into the key concepts of molecular spectroscopy and will uncover the hidden treasures this amazing new technology offers to industry. The application in real world will be shown in several showcases from different sectors ranging from recycling to pharmaceuticals. Solving industrial applications is not always easy, especially with untrained personnel. To overcome these problems, we outline a two-tier approach with a learning phase and an inference phase. The learning phase focuses on the user and reduces the complexity of the learning process and the physics. As the inference phase is solely oriented on validity and performance, we will illustrate how and why the Tegra excels in the presented applications.

  Back
 
Keywords:
Computer Vision and Machine Vision, Embedded & Robotics, Video and Image Processing, GTC Europe 2017 - ID 23161
Download:
 
Embedded GPUs in agricultural robotics: How to detect and eliminate evil plants competing with your food crops
Anil Yuce (ECOROBOTIX)
In this session you will discover how GPU processing is used for real-time plant classification and recognition on a field robot performing autonomous weeding. We will talk about the use of embedded GPUs to perform fast image pre-processing and ...Read More

In this session you will discover how GPU processing is used for real-time plant classification and recognition on a field robot performing autonomous weeding. We will talk about the use of embedded GPUs to perform fast image pre-processing and classification using deep learning, in comparison with other methods. A major focus will be on the computation time and power consumption constraints of this real-world application. In addition, we will present the advantages of our completely autonomous robot in terms of cost/labour efficiency and environmental impact.

  Back
 
Keywords:
Computer Vision and Machine Vision, Embedded & Robotics, Video and Image Processing, GTC Europe 2017 - ID 23188
Download:
 
Online Open World Face Recognition From Video Streams
Federico Pernici (MICC UNIVERSITY OF FLORENCE)
We present a novel unsupervised method for face identity learning from video sequences. The method exploits Convolutional Neural Networks for face detection and face description together with a smart learning mechanism that exploits the temporal ...Read More

We present a novel unsupervised method for face identity learning from video sequences. The method exploits Convolutional Neural Networks for face detection and face description together with a smart learning mechanism that exploits the temporal coherence of visual data in video streams. We introduce a novel feature matching solution based on Reverse Nearest Neighbour and a feature forgetting strategy that supports incremental learning with memory size control, while time progresses. It is shown that the proposed learning procedure is asymptotically stable and can be effectively applied to relevant applications like multiple face tracking and online open world face recognition from video streams. The whole system including the smart incremental learning mechanism take advantage of the GPU.

  Back
 
Keywords:
Computer Vision and Machine Vision, Intelligent Video Analytics and Smart Cities, Video and Image Processing, GTC Europe 2017 - ID 23202
Download:
 
AI Driven Environment Modeling for Autonomous Driving on NVIDIA DRIVE PX 2
Alexey Abramov (CONTINENTAL TEVES AG)
This session gives an insight into the sensor-based environment modeling for autonomous driving at Continental. We show how conventional computer vision algorithms can be combined with Artificial Intelligence to make a large step towards fully a ...Read More

This session gives an insight into the sensor-based environment modeling for autonomous driving at Continental. We show how conventional computer vision algorithms can be combined with Artificial Intelligence to make a large step towards fully autonomous driving. The presentation highlights our latest achievements in challenges like lane marking perception, construction site detection, road topology prediction, camera-based verification of radar objects. We demonstrate how the online environment model, which serves as an input for the longitudinal and lateral control of self-driving vehicles, is computed on the NVIDIA DRIVE PX 2.

  Back
 
Keywords:
Computer Vision and Machine Vision, Intelligent Machines and IoT, Self-Driving Cars, GTC Europe 2017 - ID 23218
Download:
 
Beyond Detection: GANs and LSTMs for Paying Attention to Human Presence
Rita CUCCHIARA (IMAGELAB, UNIMORE ITALY)
Computer Vision with CNNs performs well for people detection. This is not enough. A step forward can be taken to understand the aspect of people detected in low resolution, or corrupted by occlusions in the crowd; to track them in the wild; to d ...Read More

Computer Vision with CNNs performs well for people detection. This is not enough. A step forward can be taken to understand the aspect of people detected in low resolution, or corrupted by occlusions in the crowd; to track them in the wild; to detect saliency and pay attention to details only; to forecast motion and human actions. The next solutions will be provided by new neural architectures based on autoencoders and recurrent architectures, such as Generative Adversarial Networks and Long Short Term Memories. The session will present how they work, how they can be implemented on GPUs and how they are used in real applications, such as in AI cities form static and moving cameras and in collaborative environments.

  Back
 
Keywords:
Computer Vision and Machine Vision, Intelligent Video Analytics and Smart Cities, Video and Image Processing, GTC Europe 2017 - ID 23267
Download:
 
Natural, Interactive Training of Service Robots to Detect Novel Objects
Elisa Maiettini (ISTITUTO ITALIANO DI TECNOLOGIA), Giulia PASQUALE (ISTITUTO ITALIANO DI TECNOLOGIA, ICUB FACILITY AND LABORATORY FOR COMPUTATIONAL AND STATISTICAL LEARNING (IIT-MIT))
The talk will describe the solutions we devised to provide our prototype of humanoid service robot, R1, with a visual object detection system which can be trained by people in an interactive, natural way. We previously integrated Deep Learning m ...Read More

The talk will describe the solutions we devised to provide our prototype of humanoid service robot, R1, with a visual object detection system which can be trained by people in an interactive, natural way. We previously integrated Deep Learning methods on our robot, equipped with an NVIDIA Jetson TX2. The resulting recognition system could be effectively trained on the fly on board the robot and was presented at last GTC. In this talk we will discuss how we are extending it to localize and recognize multiple objects in the image, towards a system which can continuously learn to detect new objects presented by users. We will address problems as ground-truth acquisition, training/inference time, prediction robustness. We will present the system deployed on R1 and discuss open challenges.

  Back
 
Keywords:
Computer Vision and Machine Vision, Embedded & Robotics, GTC Europe 2017 - ID 23285
Download:
 
Detection and Segmentation of Road Images with Deep Learning
William Raveane (MAPSCAPE), Frank GEUJEN (MAPSCAPE)
A fundamental component required for safe autonomous driving is highly accurate maps, which contain semantic information regarding the position and content of traffic signs, lane markings, and other road features. At Mapscape, we rely heavily on ...Read More

A fundamental component required for safe autonomous driving is highly accurate maps, which contain semantic information regarding the position and content of traffic signs, lane markings, and other road features. At Mapscape, we rely heavily on deep learning to extract information from images to aid with the creation of these maps. In this presentation, we explore two parts of our process: An object detection pipeline running onboard NVIDIA Jetson devices through TensorRT capable of recognizing among 167 different traffic signs in real time, and a semantic segmentation pipeline capable of extracting up to 45 different road level features such as lanes, arrows, and other road surface signs.

  Back
 
Keywords:
Computer Vision and Machine Vision, Embedded & Robotics, HD Mapping, GTC Europe 2017 - ID 23304
Download:
 
Real-Time Data Processing With Deep Learning For Advanced Microscopy
Mykhailo VLADYMYROV (LHEP, UNIVERSITY OF BERN)
This session will show how we combine high performance GPU processing with Deep Learning (DL). We use automated tomographic imaging microscopes for various studies in physics and biology. These systems have raw data flow of up to 2GB/s, making r ...Read More

This session will show how we combine high performance GPU processing with Deep Learning (DL). We use automated tomographic imaging microscopes for various studies in physics and biology. These systems have raw data flow of up to 2GB/s, making real-time (RT) data processing mandatory. To make the system more intelligent, an advanced processing pipeline must be incorporated. So far DL inference speed doesnt allow us to apply it to all the data. To address the problem, we are designing a hybrid system, that allows DL usage for high throughput microscopy in RT. Concepts and approaches that we use to design the system will be illustrated with examples from high energy physics and biology.

  Back
 
Keywords:
Computer Vision and Machine Vision, HPC and AI, Medical Imaging and Radiology, GTC Europe 2017 - ID 23307
Download:
 
Learning to Detect Human Activities in Untrimmed Videos
Bernard Ghanem (KAUST)
In this talk, I will highlight the main research challenges facing the field of activity detection in untrimmed videos, as well as, deep learning based methods developed at KAUST to address them. Massive amounts of video data need to be processe ...Read More

In this talk, I will highlight the main research challenges facing the field of activity detection in untrimmed videos, as well as, deep learning based methods developed at KAUST to address them. Massive amounts of video data need to be processed for relevant semantic information that predominantly focuses on human activities (i.e. single human, human-to-human, and human-to-object interactions). While this problem is encountered in many real-world applications (e.g. video surveillance, large-scale video summarization, and ad placement in video platforms), automated vision solutions have been hindered by several challenges including the lack of large-scale datasets for learning and the need for real-time processing. I will highlight how deep learning can be used to tackle these challenges.

  Back
 
Keywords:
Computer Vision and Machine Vision, Intelligent Video Analytics and Smart Cities, GTC Europe 2017 - ID 23312
Download:
 
Learn How AI is Changing the World of Ophthalmology
Stefanos Apostolopoulos (RETINAI MEDICAL GMBH), Sandro DE ZANET (RETINAI MEDICAL GMBH)
The goal of this session is to illustrate how the world of ophthalmology is changing thanks to AI and deep learning. We will cover the basic aspects of eye diseases and how you can apply GPU-accelerated machine learning to improve imaging and an ...Read More

The goal of this session is to illustrate how the world of ophthalmology is changing thanks to AI and deep learning. We will cover the basic aspects of eye diseases and how you can apply GPU-accelerated machine learning to improve imaging and analysis of the eye. We present solutions to get ready for this transition by covering the latest innovations in the field of deep learning in ophthalmology, reaching for the first time human-level performance in the detection, classification and monitoring of eye disease. Furthermore, we will unravel how advances in GPU technology enable improved imaging quality for portable, low-cost Optical Coherence Tomography (3D) and Fundus (2D) imaging, the leading modalities of reference in eye care.

  Back
 
Keywords:
Computer Vision and Machine Vision, Medical Imaging and Radiology, Video and Image Processing, GTC Europe 2017 - ID 23314
Download:
 
A Performance Study of Detection Networks in Embedded Devices
Francisco Jose Garcia (UNIVERSIDAD REY JUAN CARLOS)
In this poster we compare the performance of a detection network when running in different devices. We deploy a YOLOv2 net in TK1 and TX1 embedded devices and study their performance in running time. In addition, we also test this network in a ...Read More
In this poster we compare the performance of a detection network when running in different devices. We deploy a YOLOv2 net in TK1 and TX1 embedded devices and study their performance in running time. In addition, we also test this network in a workstation equipped with a TITAN X GPU as an upper bound.
  Back
 
Keywords:
Computer Vision and Machine Vision, Embedded & Robotics, GTC Europe 2017 - ID P23026
Download:
 
New advanced method for glaucoma detection based on deep learning
Artem SEVASTOPOLSKY (YOUTH LABORATORIES)
Learn how experts from YLabs Ltd. are developing approaches for instant eye diseases assessment based on deep learning methods for eye fundus analysis. The basis of the developing technologies is formed by CNN for image segmentation trained with ...Read More

Learn how experts from YLabs Ltd. are developing approaches for instant eye diseases assessment based on deep learning methods for eye fundus analysis. The basis of the developing technologies is formed by CNN for image segmentation trained with NVIDIA GPUs, while eye fundus photos are to be taken with smartphone enhanced with special lens. YLabs Ltd. presents novel neural network architecture for glaucoma detection – “W-Net”, which, as for our knowledge, outperforms current best methods by the recognition quality by the most benchmarks.

  Back
 
Keywords:
Computer Vision and Machine Vision, Medical Imaging and Radiology, Video and Image Processing, GTC Europe 2017 - ID P23058
 
Deep Learning for Image Analysis and Synthesis
Louis Chevallier (TECHNICOLOR)
This talk will introduce a variety of use cases of deep learning for Images Analysis being studied in our lab: Image Upscaling, Image Style Transfer, Image and Panorama Stereozation and Image Interestingness Estimation. ...Read More
This talk will introduce a variety of use cases of deep learning for Images Analysis being studied in our lab: Image Upscaling, Image Style Transfer, Image and Panorama Stereozation and Image Interestingness Estimation.  Back
 
Keywords:
Computer Vision and Machine Vision, Media and Entertainment, GTC Europe 2017 - ID 23114
Download:
 
Biomedical Image and Genetic Data Analytics in Dementia and Oncology
Wiro Niessen (ERASMUS MC / DELFT UNIVERSITY OF TECHNOLOGY / QUANTIB BV)
Big data analytics methods for the large scale analysis of imaging, genetic, laboratory, and clinical data have great potential to improve our understanding of disease, and to improve disease diagnosis and prognosis. Both classical machine learn ...Read More

Big data analytics methods for the large scale analysis of imaging, genetic, laboratory, and clinical data have great potential to improve our understanding of disease, and to improve disease diagnosis and prognosis. Both classical machine learning (e.g. radiomics, multi feature classification) and deep learning methods are currently used in these domains. In this talk, I will present the results and challenges for both approaches to make impact in the context of a number of applications. Specifically, we will discuss early and differential diagnosis and improved prognosis of dementia, and improved neuro tumor characterization and treatment response prediction.

  Back
 
Keywords:
Computer Vision and Machine Vision, Medical Imaging and Radiology, GTC Europe 2017 - ID 23121
Download:
 
Deep Learning for Extracting Clinically Useful Information from Medical Images
Daniel Rueckert (IMPERIAL COLLEGE LONDON)
This talk will focus on the use of deep learning techniques for the discovery and quantification of clinically useful information from medical images. The talk will describe how deep learning can be used for the reconstruction of medical images ...Read More

This talk will focus on the use of deep learning techniques for the discovery and quantification of clinically useful information from medical images. The talk will describe how deep learning can be used for the reconstruction of medical images from undersampled data, image super-resolution, image segmentation and image classification. We will also show the clinical utility of applications of deep learning for the interpretation of medical images in applications such as brain tumour segmentation, cardiac image analysis and applications in neonatal and fetal imaging.

  Back
 
Keywords:
Computer Vision and Machine Vision, Medical Imaging and Radiology, GTC Europe 2017 - ID 23222
Download:
 
GPUs Enable Deep Neuroevolution for Vision-Based Autonomous Driving
Faustino Gomez (NNAISENSE), Jan KOUTNÍK (NNAISENSE SA)
This session introduces the work being done at NNAISENSE, a Swiss AI startup, together with Audi to advance autonomous driving through AI. It will discuss reinforcement learning and how it differs fundamentally from supervised learning (e.g. deep n ...Read More
This session introduces the work being done at NNAISENSE, a Swiss AI startup, together with Audi to advance autonomous driving through AI. It will discuss reinforcement learning and how it differs fundamentally from supervised learning (e.g. deep nets) which has received much more attention to date. We will also discuss the challenges involved in learning to drive from scratch, and how GPUs allowed to us to overcome them. After an overview of the model-car parking setup and neuroevolutionary methods used to showcase the technology, a demo will show the learning process in simulation and the behavior of the final controllers once transferred to the real car.  Back
 
Keywords:
Computer Vision and Machine Vision, Intelligent Machines and IoT, Self-Driving Cars, GTC Europe 2017 - ID 23299
Download:
 
Open Fusion Platform for Automated Driving Cars Based on Nvidia DPX2
Paulin Pekezou Fouopi (GERMAN AEROSPACE CENTER (DLR), INSTITUTE OF TRANSPORTATION SYSTEMS), Mohsen SEFATI (RWTH AACHEN, PEM CHAIR)
In this session we will present the current results of an open fusion approached based on the NVIDIA DPX2. ...Read More

In this session we will present the current results of an open fusion approached based on the NVIDIA DPX2.

  Back
 
Keywords:
Computer Vision and Machine Vision, Self-Driving Cars, GTC Europe 2017 - ID 23322
Download:
 
Cross-Domain Face Recognition Solution Based on GPU-Powered Deep Learning and Inference
Alexander Khanin (VISION LABS)
Government agencies and commercial companies today demonstrate high demand to versatile, stable and highly-efficient person identification solutions supporting cross-domain face recognition and person database clusterization in both controlled a ...Read More

Government agencies and commercial companies today demonstrate high demand to versatile, stable and highly-efficient person identification solutions supporting cross-domain face recognition and person database clusterization in both controlled and uncontrolled scenarios. Now it becomes possible to successfully resolve cross-domain face recognition challenge using deep learning and even tasks of quadratic complexity using GPU-powered inference of CNN-based face recognition algorithms. We''ll focus on (I) the concept of the GPU-powered platform for cross-domain face recognition; (II) its essential performance and critical technical characteristics; (III) reaching required accuracy and performance by using NVIDIA GPUs; (IV) examples of completed and ongoing face recognition projects

  Back
 
Keywords:
Computer Vision and Machine Vision, Intelligent Video Analytics and Smart Cities, Video and Image Processing, GTC Europe 2017 - ID 23331
Download:
 
Self-Supervised Deep Learning for Robotic Grasping
Lars Berscheid (KUKA ROBOTER GMBH)
In this talk, we will show how an industrial robot learns to grasp objects in a self-supervised manner. Starting with random grasps with a success rate of just a few percent, the robot improves its grasping success to well over 90% in a few doze ...Read More

In this talk, we will show how an industrial robot learns to grasp objects in a self-supervised manner. Starting with random grasps with a success rate of just a few percent, the robot improves its grasping success to well over 90% in a few dozen hours. In the short term, this could improve applications like bin picking and warehouse automation, while in the long term a general grasping controller could be built with the presented techniques. Already, the self-learned grasping system can handle new, unseen objects and environments with remarkable accuracy. The algorithm runs with high performance on consumer GPUs, paving the way to embedded implementations on Nvidia Jetson boards for applications.

  Back
 
Keywords:
Computer Vision and Machine Vision, Embedded & Robotics, GTC Europe 2017 - ID 23340
Download:
 
Deep Models for 3D Reconstruction
Andreas Geiger (MPI TÜBINGEN / ETH ZÜRICH)
In this talk, I will present a novel framework for deep learning with 3D data called OctNet which enables 3D CNNs on high-dimensional inputs. I will demonstrate the utility of the OctNet representation on several 3D tasks including classificatio ...Read More

In this talk, I will present a novel framework for deep learning with 3D data called OctNet which enables 3D CNNs on high-dimensional inputs. I will demonstrate the utility of the OctNet representation on several 3D tasks including classification, orientation estimation and point cloud labeling. In the second part of my talk, I will present an extension of OctNet called OctNetFusion which jointly predicts the space partitioning function with the output representation, resulting in an end-to-end trainable model for volumetric 3D reconstruction at resolutions up to 512 x 512 x 512.

  Back
 
Keywords:
Computer Vision and Machine Vision, GTC Europe 2017 - ID 23349
Download:
 
Mars Rovers to End to End Industrial Inspection Solutions: GPUs for Machine Intelligence
Mark Woods (SCISYS)
Benefit from our experiences applying Nvidia solutions including Jetson to implement high performance deep learning and vision systems, from training on high powered workstations to deployment on embedded systems. Low power, high performance, AI ...Read More

Benefit from our experiences applying Nvidia solutions including Jetson to implement high performance deep learning and vision systems, from training on high powered workstations to deployment on embedded systems. Low power, high performance, AI friendly processing allows us to provide the performance to enable us to exploit approaches and algorithms developed for space in terrestrial spin-off applications. We will use examples and demonstrations from our Mars rover development systems to show how we were easily able to leverage GPUs to advance our R&D work on autonomous science into practical terrestrial applications for the automated inspection of the built environment.

  Back
 
Keywords:
Computer Vision and Machine Vision, Intelligent Machines and IoT, Video and Image Processing, GTC Europe 2017 - ID 23350
Download:
 
PyTorch: a Framework for Fast, Dynamic Deep Learning and Scientific Computing
Soumith Chintala (FACEBOOK)
In this session, you shall be introduced to a new framework for scientific computing, mainly aimed at deep learning workloads. The framework consists of an ndarray library that natively supports GPU execution, an automatic differentiation engine ...Read More

In this session, you shall be introduced to a new framework for scientific computing, mainly aimed at deep learning workloads. The framework consists of an ndarray library that natively supports GPU execution, an automatic differentiation engine that is flexible and fast, and an optimization package for gradient based optimization methods. We shall discuss practical workflows, our features on top of python multiprocessing for efficient parallel data loaders and finally we shall briefly look at our upcoming just-in-time Tensor compiler to fuse computations and execute them more efficiently.

  Back
 
Keywords:
Computer Vision and Machine Vision, Tools and Libraries, GTC Europe 2017 - ID 23373
Download:
 
Efficient inference with TensorRT
Han Vanholder (NVIDIA)
In Deep Learning, Inference is where neural networks deliver insights. What started with images is quickly expanding to include speech, NLP and video. As data sets get bigger, networks get deeper and more complex, and latency requirements get ti ...Read More

In Deep Learning, Inference is where neural networks deliver insights. What started with images is quickly expanding to include speech, NLP and video. As data sets get bigger, networks get deeper and more complex, and latency requirements get tighter, GPUs are the ideal platform to accelerate these workloads, both for high batch and low-latency use-cases. In this talk, youll learn how inference gets done on GPUs, and get the latest on TensorRT 3.0, the latest version of NVIDIAs inference engine.

  Back
 
Keywords:
Computer Vision and Machine Vision, Data Center and Cloud Infrastructure, GTC Europe 2017 - ID 23425
Download:
 
Democratizing Autonomous Driving with Cameras and A.I.
Hugo Fozzati (AUTOX)
Today, there are two major paradigms for vision-based autonomous driving systems: mediated perception approaches that parse an entire scene to make a driving decision, and behavior reflex approaches that directly map an input image to a driving ...Read More

Today, there are two major paradigms for vision-based autonomous driving systems: mediated perception approaches that parse an entire scene to make a driving decision, and behavior reflex approaches that directly map an input image to a driving action by a regressor. In this paper, we propose a third paradigm: a direct perception based approach to estimate the affordance for driving. We propose to map an input image to a small number of key perception indicators that directly relate to the affordance of a roadundefinedtraffic state for driving. Our representation provides a set of compact yet complete descriptions of the scene to enable a simple controller to drive autonomously.

  Back
 
Keywords:
Computer Vision and Machine Vision, Large Scale and Multi-Display Visualization, Self-Driving Cars, GTC Europe 2017 - ID 23427
 
Building Self-Driving Delivery Robots
Kristjan Korjus (STARSHIP TECHNOLOGIES)
Starship Technologies is developing the future of delivery self-driving robots that will bring goods to people all around the world. We have entered commercial pilots with hundreds of robots driving along the sidewalks across the United States a ...Read More

Starship Technologies is developing the future of delivery self-driving robots that will bring goods to people all around the world. We have entered commercial pilots with hundreds of robots driving along the sidewalks across the United States and four countries in Europe. Soon there will be thousands and millions of robots around the world. The talk gives an overview of the story, business, and technology of Starship Technologies.

  Back
 
Keywords:
Computer Vision and Machine Vision, Embedded & Robotics, Self-Driving Cars, GTC Europe 2017 - ID 23443
Download:
 
How Game Engines Can Empower Projects Across the Automotive Sector
Doug WOLFF (EPIC GAMES)
We will look at 3 main areas of the automotive product life cycle, each with an expert panelist, these will include design, engineering and marketing. For design, we will see how short-iteration cycles and rich experiences can make the next-leve ...Read More

We will look at 3 main areas of the automotive product life cycle, each with an expert panelist, these will include design, engineering and marketing. For design, we will see how short-iteration cycles and rich experiences can make the next-level of design decisions. For engineering, we will look at how a game engine can fast-track on-vehicle system development. And finally, marketing will show game engines can drive consumer engagement. Panelists are: Árpád Takács (AImotive, AI Researcher and Outreach Scientist), Kian Saemian (Mackevision, Senior Business Development Manager) and Daniel Motus (BMW, Head of Cubing, Virtual Reality Interior).

  Back
 
Keywords:
Computer Vision and Machine Vision, Self-Driving Cars, Real-Time Graphics, GTC Europe 2017 - ID 23453
Download:
 
Is Augmented Reality too Expensive for Business?
Wolfgang STELZLE (RE'FLEKT)
Augmented Reality has been around for a while now with plenty of major investments made to develop the technology. Yet years have passed and we still dont see AR in our daily business lives despite such obvious benefits. At best we are only seei ...Read More

Augmented Reality has been around for a while now with plenty of major investments made to develop the technology. Yet years have passed and we still dont see AR in our daily business lives despite such obvious benefits. At best we are only seeing sandbox projects for consumer marketing and attention grabbing stunts. Is AR tech not good enough for industrial applications or is it simply too expensive? More importantly, what do AR solution providers collectively need to do to open up their market for the masses?

  Back
 
Keywords:
Computer Vision and Machine Vision, Intelligent Machines and IoT, GTC Europe 2017 - ID 23477
Download:
Data Center and Cloud Infrastructure
Presentation
Media
Designing the Collaborative Virtual Workspace Infrastructure
Jan WURSTER (ESI GROUP)
Presenting the concept of a collaborative, immersive and user-centric virtual engineering space, we discuss the challenges in designing the engineering workspace of the future, leveraging VR/AR solutions provided by the developing VR/AR market t ...Read More

Presenting the concept of a collaborative, immersive and user-centric virtual engineering space, we discuss the challenges in designing the engineering workspace of the future, leveraging VR/AR solutions provided by the developing VR/AR market through on-premise and public cloud infrastructure. We'll present the challenges of delivering immersive content to arbitrary devices, user-centric design, modalities and pipeline implementation for collaborative virtual spaces to support both local and remote users. An introduction of the technical foundations will cover solution architectures extending to specific rendering and content streaming techniques, virtualization and the VR Datacentre all combined to enable high definition, interactive content in shared, rich immersive experiences.

WebVR enabled streaming

Live demo set-up at GTC Europe

 

  Back
 
Keywords:
Data Center and Cloud Infrastructure, Rendering and Ray Tracing, Real-Time Graphics, GTC Europe 2017 - ID 23047
Download:
 
Changing gear for accelerating deep learning
Yu WANG (LEIBNIZ-RECHENZENTRUM)
The Leibniz Supercomputing Centre of the Bavarian Academy of Sciences and Humanities deployed several GPU systems, including a DGX-1 and Openstack cloud based GPU virtual servers (with Pascal 100) since the start of 2017. Our users tested scalab ...Read More

The Leibniz Supercomputing Centre of the Bavarian Academy of Sciences and Humanities deployed several GPU systems, including a DGX-1 and Openstack cloud based GPU virtual servers (with Pascal 100) since the start of 2017. Our users tested scalability of Deep learning on DGX-1, trained Deep learning models for simulating Quantum experiments and performed numerical simulations of fluid motion, utilizing the multiple, NVlinked GPUs on DGX-1. These results demonstrate that GPU based computational solutions, such as DGX-1, are valuable computational assets of the Bavarian academic computational infrastructure.

  Back
 
Keywords:
Data Center and Cloud Infrastructure, Data Center and Cloud Infrastructure, HPC and Supercomputing, GTC Europe 2017 - ID P23049
 
Hard Facts - Benchmarking GRID-Accelerated Remote Desktop User Experience
Ruben Spruijt (FRAME), Benny TRITSCH (RDSGURUS)
In this session, NVIDIA GRID Community Advisors Ruben Spruijt and Benny Tritsch present their latest findings on benchmarking user experience performance in GRID-accelerated environments hosted on-premises and in the cloud. Get in-depth informat ...Read More

In this session, NVIDIA GRID Community Advisors Ruben Spruijt and Benny Tritsch present their latest findings on benchmarking user experience performance in GRID-accelerated environments hosted on-premises and in the cloud. Get in-depth information on the latest versions of Citrix XenApp/XenDesktop, VMware Horizon and Microsoft RDS when accelerated by NVIDIA GPUs. What is the performance impact caused by remoting protocol settings, latency and common WAN scenarios? Hundreds of recorded screen videos and telemetry data sets, combined with a unique visualisation tool, allow Ruben and Benny to analyse and compare the performance of selected GRID-accelerated remote desktops and VDI scenarios, live on stage.

  Back
 
Keywords:
Data Center and Cloud Infrastructure, GTC Europe 2017 - ID 23086
Download:
 
SIZE DOES MATTER! - The Ultimate Sizing and Optimization Guide for GRID Environments
Roy TEXTOR (TEXTOR IT)
Deep dive into the sizing and optimisation of your NVIDIA GRID environment. ...Read More

Deep dive into the sizing and optimisation of your NVIDIA GRID environment.

  Back
 
Keywords:
Data Center and Cloud Infrastructure, Large Scale and Multi-Display Visualization, Performance Optimization, GTC Europe 2017 - ID 23087
Download:
 
Real World Implementation (and snares) of a High Performance NVIDIA GRID Infrastructure
Jan Hendrik Meier (GRIMME LANDMASCHINENFABRIK GMBH & CO. KG), Thomas REMMLINGER (NVIDIA)
The Grimme Group is a medium-sized company with the Headquarter based in the North of Germany. Grimme is the world market leader for potato technology. In 2016 Grimme launched a project to replace their existing CAD-Software and decided to relieve th ...Read More
The Grimme Group is a medium-sized company with the Headquarter based in the North of Germany. Grimme is the world market leader for potato technology. In 2016 Grimme launched a project to replace their existing CAD-Software and decided to relieve the CAD-Workstation infrastructure. During this session you will get valuable information as to why Grimme decided to use NVIDIA GRID and what challenges came up during the implementation and rollout. Learn more about the projects steps and their associated technical details. Get an idea how to plan and implement a very successful NVIDIA GRID Project.  Back
 
Keywords:
Data Center and Cloud Infrastructure, Other, Real-Time Graphics, GTC Europe 2017 - ID 23129
Download:
 
Empowering Radiologists with NVIDIA GRID
Hans Kraaijeveld (CLIENT ICT GROEP)
In this session, we will describe the successful proof of concept in which a radiology desktop computer was replaced by a thin client and a VDI desktop, hosted in the hospital's data center. We will also show you what the challenges were and ...Read More

In this session, we will describe the successful proof of concept in which a radiology desktop computer was replaced by a thin client and a VDI desktop, hosted in the hospital's data center. We will also show you what the challenges were and what the solution has brought the hospital in terms of advantages in comparison with the old situation. The case is very interesting for anyone wanting to learn more about the possibilities of virtualised graphics.

  Back
 
Keywords:
Data Center and Cloud Infrastructure, Large Scale and Multi-Display Visualization, Medical Imaging and Radiology, GTC Europe 2017 - ID 23180
Download:
 
Enabling Global Growth with NVIDIA GRID
Rody KOSSEN (AWL TECHNIEK), Jits Langedijk (PQR)
During this session, you will learn how AWL Techniek, a a global operating specialist in designing and building state-of-the-art automated welding robots, rapidly increased their market share in worlds best fully automated welding robots. These ...Read More

During this session, you will learn how AWL Techniek, a a global operating specialist in designing and building state-of-the-art automated welding robots, rapidly increased their market share in worlds best fully automated welding robots. These state-of-the-art robots are used in the automotive industry all over the world. This rapid growth was made possible with the use of NVIDIA GRID technology combined with Citrix XenDesktop virtualization techniques. With these solutions AWL Techniek is able to shorten their time-to-market, both with their robots as well as with new branch locations all over the globe.  

  Back
 
Keywords:
Data Center and Cloud Infrastructure, Performance Optimization, GPU Virtualization, GTC Europe 2017 - ID 23075
 
Gil Bloch (MELLANOX)
Come join us, and learn how to build a data-centric GPU clusters for artificial intelligence.  We will briefly present the state-of-the-art techniques for distributed Machine Learning, and the special requirements they impose on the GPU clu ...Read More

Come join us, and learn how to build a data-centric GPU clusters for artificial intelligence.  We will briefly present the state-of-the-art techniques for distributed Machine Learning, and the special requirements they impose on the GPU cluster. Additionally, we will present an overview of interconnect technologies used to scale and accelerate distributed Machine Learning.   During the session we will cover RDMA, NVIDIA's GPUDirect RDMA and GPUDirect Asynch as well as in-network-computing and how the use of those technologies enables new level of scalability and performance in large scale deployments in artificial intelligence and high performance computing.    

  Back
 
Keywords:
Data Center and Cloud Infrastructure, HPC and AI, HPC and Supercomputing, GTC Europe 2017 - ID 23200
Download:
 
Accelerating AI in Cosmetics – The Case of L'Oréal's Smart Hair Brush
Jean-Loup Loyer (L'ORÉAL RESEARCH&INNOVATION)
The cosmetics industry is undergoing tremendous change under the hectic evolution of more-demanding-than-ever consumers, explosion of IoT and fierce competition from start-ups. L’Oréal-Kérastase&r ...Read More
The cosmetics industry is undergoing tremendous change under the hectic evolution of more-demanding-than-ever consumers, explosion of IoT and fierce competition from start-ups. L’Oréal-Kérastase’s Smart Hair Coach is a perfect example of how the combination of AI and connected devices can lead to a superior customer service and obtain novel high-value customer insights. Thanks to its embedded sensors, the brush analyses the user’s movements and hair characteristics, so as to recommend relevant hair products and good brushing practices. GPU technology allows faster training on terabytes of data and inference on a larger number of calls per second. The enhanced computational performance will be illustrated on the classification of brushing movement using Long Short-Term Memory (LSTM) models.

 

  Back
 
Keywords:
Data Center and Cloud Infrastructure, Intelligent Machines and IoT, Signal and Audio Processing, GTC Europe 2017 - ID 23253
Download:
 
Deep Imaging. Quantitative Biomarkers for Clinical Decision Making.
Joerg Aumueller (SIEMENS HEALTHINEERS)
The transformation towards value-based healthcare needs inventive ways to lower cost and increase outcomes. Artificial Intelligence is key to realizing value-based care. Turning medical images into biomarkers helps to increase effectiveness of c ...Read More

The transformation towards value-based healthcare needs inventive ways to lower cost and increase outcomes. Artificial Intelligence is key to realizing value-based care. Turning medical images into biomarkers helps to increase effectiveness of care through quantitative imaging.

  Back
 
Keywords:
Data Center and Cloud Infrastructure, Medical Imaging and Radiology, Video and Image Processing, GTC Europe 2017 - ID 23117
Download:
 
Self-Healing Maps for Autonomous Driving
Sanjay Sood (HERE TECHNOLOGIES)
Self-Driving vehicles require a high definition, continuously updating self-healing map to help the vehicle operate safely and comfortably. It needs real-time, accurate and semantically rich data to pinpoint its lane level position, and enable the ve ...Read More
Self-Driving vehicles require a high definition, continuously updating self-healing map to help the vehicle operate safely and comfortably. It needs real-time, accurate and semantically rich data to pinpoint its lane level position, and enable the vehicle to make proactive maneuvers in response to changes that affect driving conditions. These are critical issues that HERE is addressing, leveraging machine learning and crowdsourced data, with its HD Live Map by providing precise positioning on the road and accurate planning of vehicle control maneuvers beyond sensor visibility. HERE is closing the data loop from vehicle to cloud, utilizing real-time vehicle sensor data thus turning commercial vehicles into a crowd of data collectors to help heal our map.  Back
 
Keywords:
Data Center and Cloud Infrastructure, HD Mapping, Self-Driving Cars, GTC Europe 2017 - ID 23376
 
Evaluating Windows 10: Learn Why Your Users Need GPU Acceleration
Erik BOHNHORST (NVIDIA), Nachiket KARMARKAR (NVIDIA)
Learn why EVERY remote user should have GPU resources available to them. We''ll discuss the advantages end-users experience once their virtual desktopsundefinedsessions have GPU capabilities. Recent data from the NVIDIA GRID Performance ...Read More

Learn why EVERY remote user should have GPU resources available to them. We''ll discuss the advantages end-users experience once their virtual desktopsundefinedsessions have GPU capabilities. Recent data from the NVIDIA GRID Performance Engineering team shows a significant impact GPUs like the Tesla M10 has on knowledge workers. The data includes real user testing and scientific data like end user latency, remoted frames, bandwidth, and CPU utilization, which all play a significant role in the overall user experience.

  Back
 
Keywords:
Data Center and Cloud Infrastructure, GTC Europe 2017 - ID 23428
Download:
 
Global roll-out of the Digital Reality Hub at Volkswagen - Today's success story and future developments with Innoactive
Daniel Seidl (INNOACTIVE)
The need for a standardized enterprise platform with a unified user interface to streamline virtual, augmented and mixed reality applications increases constantly. The Innoactive® Hub, the leading mixed reality enterprise platform, which includes ...Read More
The need for a standardized enterprise platform with a unified user interface to streamline virtual, augmented and mixed reality applications increases constantly. The Innoactive® Hub, the leading mixed reality enterprise platform, which includes an on-prem installation option for enterprises with high data privacy requirements, offers Volkswagen the perfect platform to fulfil this need. Volkswagen is able to realize many use cases like VR training, planning or virtual workshops on the platform in a short amount of time and deploy them worldwide to their users. Volkswagen and Innoactive invite to an insight into todays success story and future developments.  Back
 
Keywords:
Data Center and Cloud Infrastructure, Education and Training, Large Scale and Multi-Display Visualization, GTC Europe 2017 - ID 23442
Deep Learning and AI
Presentation
Media
The IBM Power of AI
Ulrich WALTER (IBM), Eberhard Faust (INS), Welf Wustlich (PLANET GMBH)
In this session we will discuss with our partners INS GmbH and Planet GmbH the advantages of IBM POWER systems in combination with NVIDIA technology as an ideal choice for a performant, reliable and highly scalable AI infrastructure. By combinin ...Read More

In this session we will discuss with our partners INS GmbH and Planet GmbH the advantages of IBM POWER systems in combination with NVIDIA technology as an ideal choice for a performant, reliable and highly scalable AI infrastructure. By combining the platform for deep learning with IBM POWER AI software, enterprises can rapidly deploy a fully optimized and supported platform for machine learning with blazing performance. The PowerAI platform includes the most popular machine learning frameworks and their dependencies, and it is built for easy and rapid deployment.

  Back
 
Keywords:
Deep Learning and AI, Other, GTC Europe 2017 - ID 23488
Download:
 
Deep Learning in Automotive - Beyond Autonomous Driving
Daniel Weimer (VOLKSWAGEN AG)
This talk gives an overview about Deep Learning and the overall field of AI with a focus on automotive applications beyond autonomous driving. Deep Learning solutions as the driving force of AI enables the transition of Volkswagen towards a data ...Read More

This talk gives an overview about Deep Learning and the overall field of AI with a focus on automotive applications beyond autonomous driving. Deep Learning solutions as the driving force of AI enables the transition of Volkswagen towards a data driven company - this talk gives insights on how this transitions has been already implemented.    

  Back
 
Keywords:
Deep Learning and AI, Other, GTC Europe 2017 - ID 23220
Download:
 
GPU-accelerated Deep Neural Networks for End-to-end Differentiable Planning and Reasoning
Tim Rockt#228;schel (UNIVERSITY OF OXFORD)
This session discusses tree-structured neural networks for planning and reasoning and the computational challenges that arise for this promising class of models. Despite the tremendous success of deep learning in recent years, we lack neural net ...Read More

This session discusses tree-structured neural networks for planning and reasoning and the computational challenges that arise for this promising class of models. Despite the tremendous success of deep learning in recent years, we lack neural networks that facilitate explicit planning and reasoning. Automated planning and reasoning encompasses tree structures over possible future states and provides elegant ways for combining neural and symbolic computation, as well as model-free and model-based reinforcement learning. While these models are promising extensions to more established architectures, tree structures pose unique challenges to GPU computation. I will talk about our efforts on addressing these challenges for reasoning in knowledge bases and model-based deep reinforcement learning.

  Back
 
Keywords:
Deep Learning and AI, GTC Europe 2017 - ID 23372
Download:
Presentation
Media
 
Keywords:
,
Education and Training
Presentation
Media
Learning with Virtual Reality at Deutsche Bahn
Usman Ghias (DB SYSTEL GMBH)
How virtual reality and serious gaming is used in making training of employees better at Deutsche Bahn. The session will share the story of how we started to use virtual reality with example of a successful project that is being used to train more th ...Read More
How virtual reality and serious gaming is used in making training of employees better at Deutsche Bahn. The session will share the story of how we started to use virtual reality with example of a successful project that is being used to train more than 5000 employees. Will also shed light on common challenges that were faced while developing VR applications for non-gaming users and how they were tackled. It will also briefly cover other use cases, success stories, do's and dont of using VR in training & education.  Back
 
Keywords:
Education and Training, Virtual Reality and Augmented Reality, Game Development, GTC Europe 2017 - ID 23105
Download:
 
Virtual Reality's African Future
Judith OKONKWO (IMISI 3D), Olutade AJIBOYE (IMISI 3D)
Using the Nigerian experience as a case study, we explore the adoption of virtual reality in a frontier market. In 2016, Imisi 3D, a virtual reality creation lab set up in Lagos with the dual purpose of growing a community of content creators fo ...Read More

Using the Nigerian experience as a case study, we explore the adoption of virtual reality in a frontier market. In 2016, Imisi 3D, a virtual reality creation lab set up in Lagos with the dual purpose of growing a community of content creators for the extended reality technologies and driving engagement and adoption of these technologies. In a country known for consumption when it comes to technology, this was a dedicated effort to change the narrative to creation while positioning these technologies as tools for creating solutions. Imisi 3D went on to host Africa's first VR hackathon, started local AR/VR meetups, and an online community. Ultimately we will reflect on lessons learned from the journey so far, and consider what the future holds for the continent and the rest of the world.  

  Back
 
Keywords:
Education and Training, Other, GTC Europe 2017 - ID 23281
Download:
Embedded & Robotics
Presentation
Media
License plate recognition on Tegra X1
Burak ÖZKALAYCI (ASELSAN)
An embedded license plate recognition system, implemented on Tegra X1, performs with an accuracy over 95% in day and night conditions. The license plate recognition system is posed of two main parts, plate detector and optical character reader ( ...Read More

An embedded license plate recognition system, implemented on Tegra X1, performs with an accuracy over 95% in day and night conditions. The license plate recognition system is posed of two main parts, plate detector and optical character reader (OCR). The plate detector is a cascaded one based on decision trees and the OCR engine is a deep convolutional neural network which sustains the robustness of the recognition system. Both the detector and OCR engines are trained with a labeled character dataset obtained from traffic surveillance cameras. The described license plate recognition system operates on Tegra X1 platform for real-time traffic monitoring via 2048x1536 video streams.

  Back
 
Keywords:
Embedded & Robotics, Intelligent Video Analytics and Smart Cities, Video and Image Processing, GTC Europe 2017 - ID P23029
 
Parallel Path Evaluation for Mobile Robot Navigation
Ulises Orozco (CETYS UNIVERSIDAD)
This work presents an approach for parallel path evaluation for mobile robot navigation. To achieve the mobile robot navigation the system employs the integration of template-matching filters for obstacle detection and evolutionary artificial po ...Read More

This work presents an approach for parallel path evaluation for mobile robot navigation. To achieve the mobile robot navigation the system employs the integration of template-matching filters for obstacle detection and evolutionary artificial potential field (EAPF) for path planning. The recognition system employs a digital camera to sense the environment of the mobile robot. The captured scene is processed by a bank of space variant filters to find the obstacles in the workspace. When the position and size of the obstacles are already known, the path planning system employs the EAPF to derive an optimal path for mobile robot navigation. The path generation and evaluation is performed employing parallel computing on GPU to reduce the amount of computation time.

  Back
 
Keywords:
Embedded & Robotics, Intelligent Machines and IoT, Self-Driving Cars, GTC Europe 2017 - ID P23041
 
Robot augmented reality
Raffaello BONGHI (RNEXT.IT)
The idea is to allow the robot to interact with obstacles that are not really present in the environment, but have been drawn by an external operator. The robot uses different control techniques to navigate in an environment where there are both ...Read More

The idea is to allow the robot to interact with obstacles that are not really present in the environment, but have been drawn by an external operator. The robot uses different control techniques to navigate in an environment where there are both real and virtual obstacles that must be avoided. The path planner is capable of recognize both real and virtual obstacles, building a trajectory that treats both of them in the same way. This technique can be useful during tests and staff trainings, giving the opportunity to try to drive a robot in hard virtual environments, drawn on the basis of real physic environments.

  Back
 
Keywords:
Embedded & Robotics, HD Mapping, Intelligent Machines and IoT, GTC Europe 2017 - ID P23051
 
PIXEVIA: AI Based, Real-Time Computer Vision System for Drones and Smart Cities
Mindaugas EGLINSKAS (MAGMA SOLUTIONS, UAB)
Modern computing hardware and NVIDIA Jetson TX1 / TX2 performance create new possibilities for drones and enable autonomous AI systems, where image processing can be done on-board during flight or near the camera. We'll present how PIXEVIA s ...Read More

Modern computing hardware and NVIDIA Jetson TX1 / TX2 performance create new possibilities for drones and enable autonomous AI systems, where image processing can be done on-board during flight or near the camera. We'll present how PIXEVIA system covers vision processing and AI tasks for drones, e.g., image stabilization, position estimation, object detection, tracking, and classification using deep neural networks, and self-evolvement after deployment. We'll describe software frameworks Caffe/Tensorflow with cuDNN, VisionWorks, and NVIDIA CUDA to achieve real-time vision processing and object recognition. Real-world use cases with drone manufacturers Aerialtronics and Squadrons Systems, and with smart city applications in Vilnius and Tallinn will be presented during this talk.

  Back
 
Keywords:
Embedded & Robotics, Intelligent Video Analytics and Smart Cities, Video and Image Processing, GTC Europe 2017 - ID 23320
Download:
 
Deep Reinforcement Learning for Robotics Using DIANNE
Elias DE CONINCK (GHENT UNIVERSITY - IMEC), Steven BOHEZ (GHENT UNIVERSITY), Tim VERBELEN (IMEC)
We will show a complete system where a mobile robot learns to locate and retrieve objects using reinforcement learning and the DIANNE deep learning framework. DIANNE is used to train models on high-end GPU systems in the cloud with simulated dat ...Read More

We will show a complete system where a mobile robot learns to locate and retrieve objects using reinforcement learning and the DIANNE deep learning framework. DIANNE is used to train models on high-end GPU systems in the cloud with simulated data. The trained network is then transferred to the robot equipped with a Jetson TX1 embedded GPU. The Jetson TX1 allows the robot to process real-time information from rich sensors mounted on the robot or deployed in the environment.

  Back
 
Keywords:
Embedded & Robotics, Intelligent Machines and IoT, Tools and Libraries, GTC Europe 2017 - ID 23175
Download:
 
Case study: How we merged drones, machine learning and image data processing within strategy consulting
Adam WISNIEWSKI (PWC POLAND)
PwC Drone Powered Solutions is a first global center of excellence focusing on fusion of drone technology with other technologies including but not limited to machine learning, photogrammetry and image data processing. Adam Wi?niewski will show ...Read More

PwC Drone Powered Solutions is a first global center of excellence focusing on fusion of drone technology with other technologies including but not limited to machine learning, photogrammetry and image data processing. Adam Wi?niewski will show examples on how DPS worked with clients from various industries on testing applications and deployment of technologies enabled by drones in their operations. We have developed end-to-end drone powered solutions for capital projects monitoring, infrastructure maintenance, mining operations supervision, environmental protection, insurance claims assessment and many others.

  Back
 
Keywords:
Embedded & Robotics, HD Mapping, Video and Image Processing, GTC Europe 2017 - ID 23210
Download:
 
AI-Augmented Inspections: Automatizing Drone Workflow
Massimiliano Versace (NEURALA)
Deep learning neural networks add brain-like functions to autonomous systems, such as drones, to help inspections by drone for cell towers, roofs and infrastructure. The manual process of watching a drone video is tiring and prone to human error. A ...Read More
Deep learning neural networks add brain-like functions to autonomous systems, such as drones, to help inspections by drone for cell towers, roofs and infrastructure. The manual process of watching a drone video is tiring and prone to human error. Advances in Neuroscience and Computer are able to take over basic functions of unmanned vehicles and perform increasingly human-like activities, such as object recognition, obstacle avoidance, and inspection of complex machines and objects. Max Versace will explain how drones use embedded GPUs coupled with relatively inexpensive sensors to enable machines to sense and navigate intelligently, and safely, inspect their environment. The talk will illustrate GPU-compatible working "mini-brain" that can drive drones and power smart inspections.  Back
 
Keywords:
Embedded & Robotics, Intelligent Machines and IoT, Self-Driving Cars, GTC Europe 2017 - ID 23221
 
Designing a software framework for automated driving
Sebastian Ohl (ELEKTROBIT AUTOMOTIVE GMBH)
Developing highly automated driving (HAD) systems requires various different data processing stages. Using a software framework for HAD systems such as EB robinos can provide the basic software modules to streamline this process. It provides bui ...Read More

Developing highly automated driving (HAD) systems requires various different data processing stages. Using a software framework for HAD systems such as EB robinos can provide the basic software modules to streamline this process. It provides building blocks to develop different HAD applications ranging from valet parking to highway driving. Before mass production, the development of HAD systems needs to change from rapid prototyping to an embedded platform. In this presentation we show how we ported our HAD software framework EB robinos to NVIDIA DRIVE PX.

  Back
 
Keywords:
Embedded & Robotics, Self-Driving Cars, GTC Europe 2017 - ID 23257
Download:
 
Doming the Beast: Achieving Predictability on Drive PX2
Marko Bertogna (UNIVERSITY OF MODENA), Paolo GAI (EVIDENCE)
High-performance embedded platforms, like Nvidia Parker and upcoming Xavier architecture, have the potential of revolutionizing traditional safety-critical domains, where innovative automotive and avionic applications are being proposed to safel ...Read More

High-performance embedded platforms, like Nvidia Parker and upcoming Xavier architecture, have the potential of revolutionizing traditional safety-critical domains, where innovative automotive and avionic applications are being proposed to safely replace human activities. However, these domains require sound guarantees be given not only on the functional correctness but also on the timing delays of the critical activities, according to well defined safety standards (e.g., ISO26262). In this talk, we will explain how predictability can be achieved on inherently unpredictable multi-core systems, analyzing the main timing bottlenecks of these challenging platforms, and presenting a holistic framework that aims at overcoming them to achieve predictable performance.

  Back
 
Keywords:
Embedded & Robotics, Self-Driving Cars, Real-Time Graphics, GTC Europe 2017 - ID 23182
Download:
 
Real-Time Scanning with Jetson TX For Skin Cancer Detection
Jeremy MASSEY (IKO PTE LTD), Michael GIELDA (ANTMICRO)
Iko is developing a skin imaging system for clinical use thats faster, cheaper and simpler to use in the field, offering vastly improved accuracy over current imaging methods. Antmicro is developing the Jetson TX-based handheld embedded device t ...Read More

Iko is developing a skin imaging system for clinical use thats faster, cheaper and simpler to use in the field, offering vastly improved accuracy over current imaging methods. Antmicro is developing the Jetson TX-based handheld embedded device to be used in the system, incorporating real time depth image processing, spatial tracking and 3D visualisation. This session will present the limitations of current skin imaging methods for clinical use, including detecting and tracking potential skin cancer, along with a detailed presentation of the system design and development process. This session is ideal for those interested in the role GPU technology can play in medical imaging applications, and offers a high level view into the design and development process of such a system.

  Back
 
Keywords:
Embedded & Robotics, Medical Imaging and Radiology, Video and Image Processing, GTC Europe 2017 - ID 23374
Download:
 
Real-Time Face Recognition on Jetson Tx2 using TensorRT
Tamas GROBLER (ULTINOUS)
We present a face recognition system that can recognize multiple persons parallel in real-time running on a single Jetson TX2. Due to rapid progress in deep learning accuracy of face recognition has surpassed human level recently. GPUs became th ...Read More

We present a face recognition system that can recognize multiple persons parallel in real-time running on a single Jetson TX2. Due to rapid progress in deep learning accuracy of face recognition has surpassed human level recently. GPUs became the major platform to train and run deep learning models. Speed of NVidia GPUs on deep learning tasks is increasing rapidly due to hardware and software optimizations. We present a system that combines the most accurate face detection and recognition models with the fastest software stack. Combined with a 4K camera the system can recognize over 10 persons parallel in crowd situations even from 10 meter range. The system can be deployed to low power embedded environments such as drones.

  Back
 
Keywords:
Embedded & Robotics, Intelligent Video Analytics and Smart Cities, Video and Image Processing, GTC Europe 2017 - ID 23445
Download:
Game Development
Presentation
Media
Agency in Multi-User and Collaborative VR Enabled By NVIDIA "MUVR" Virtual Machines
Cyril Tuschi (YOU-VR)
A TALK ABOUT THE JOYS AND HURDLES OF DEVELOPING MULTI-SENSORY MULTI-PLAYER VR EXPERIENCES. You-VR develops software and content for narrative and B2B multi-sensory multi-user VR experiences. Within a series of test set-ups, You-VR attempts to re ...Read More

A TALK ABOUT THE JOYS AND HURDLES OF DEVELOPING MULTI-SENSORY MULTI-PLAYER VR EXPERIENCES. You-VR develops software and content for narrative and B2B multi-sensory multi-user VR experiences. Within a series of test set-ups, You-VR attempts to reach a perfect equilibrium between personal agency, UX convenience and affordability. The aim is to combine multi-user VR (4 people), with full-body avatars, including hand- and eye-tracking, wirelessly connected to an array of hi-end GPUs in virtual machines - all laser tracked on a large-scale playfield.

  Back
 
Keywords:
Game Development, Media and Entertainment, Real-Time Graphics, GTC Europe 2017 - ID 23206
Download:
 
Discover the next level of Virtual Reality Experiences and what it takes to bring them alive.
Leif Petersen (IGNYTE GMBH)
This talk will give a guideline of what it takes to create the next level of immersive entertainment. VR location based entertainment lives at the forefront of this exciting new medium. Technologies from laser-scanning, photogrammetry, volumetric cap ...Read More
This talk will give a guideline of what it takes to create the next level of immersive entertainment. VR location based entertainment lives at the forefront of this exciting new medium. Technologies from laser-scanning, photogrammetry, volumetric capture and others will be showcased to give an understanding of how we can achieve photo-real results. Leif has a 20 year working history in visual effects and has been a long time virtual reality enthusiast since the 90s. His talk will show first hand examples of these technologies and how they can be applied. Leif will outline how modern GPU´s help to create the next level of immersion. Recently finished VR projects for Audi as well as the location based multiplayer platform HOLOGATE will serve as examples of how this technology can be applied.  Back
 
Keywords:
Game Development, HPC and AI, Real-Time Graphics, GTC Europe 2017 - ID 23229
Download:
 
Unlocking Europe's Potential in the VR/AR Industry
Daan Kip (VRBASE), Sara Lisa VOGL (VRBASE)
Daan Kip and Sara Lisa Vogl, founders of VRBASE, the first VR/AR incubator in Europe, will give you insight into the development of the European VR/AR industry. They believe that Europe has the potential to be the global leader in high-end imm ...Read More
Daan Kip and Sara Lisa Vogl, founders of VRBASE, the first VR/AR incubator in Europe, will give you insight into the development of the European VR/AR industry. They believe that Europe has the potential to be the global leader in high-end immersive content creation. In order to unlock Europe’s potential, they’re bringing together the leading engineers, designers and artists to create in their physical hubs. Within this collaborative space, the community is able to push the boundaries of the medium and drive forward the unification of art, science and technology. To spark the industry, VRBASE is setting up a VC fund to invest in early stage startups. In this talk, you'll learn why this fund was created and their ambitions and strategy to accelerate the growth of start-ups in Europe.
 
  Back
 
Keywords:
Game Development, Virtual Reality and Augmented Reality, Media and Entertainment, GTC Europe 2017 - ID 23177
 
Intro to VRWorks: How to optimize your VR application for minimal latency and maximum performance
Dominic ESKOFIER (NVIDIA)
Development for Virtual Reality is a hunt for each millisecond of latency its the one metric that needs to be perfect for an immersive and comfortable experience. Additionally, due to the way VR content is rendered, it takes up to 7x the amount ...Read More

Development for Virtual Reality is a hunt for each millisecond of latency its the one metric that needs to be perfect for an immersive and comfortable experience. Additionally, due to the way VR content is rendered, it takes up to 7x the amount of GPU throughput needed when compared to traditional gaming. In Dominic Eskofiers talk, youll learn how to maximize both framerate and visual quality of your Virtual Reality app by using sophisticated rendering techniques built into popular game engines, NVIDIAs SDKs and modern GPUs.

  Back
 
Keywords:
Game Development, Performance Optimization, Tools and Libraries, GTC Europe 2017 - ID 23448
Download:
 
Creative AI - Disrupting the Entertainment and Design Industries
Eric RISSER (ARTOMATIX)
Recent breakthroughs in Deep Learning have led to the inception of "Creative AI", a new branch of machine learning dedicated to mimicking human-like artistic creativity. This talk introduces the emerging field as well as several of the core ...Read More
Recent breakthroughs in Deep Learning have led to the inception of "Creative AI", a new branch of machine learning dedicated to mimicking human-like artistic creativity. This talk introduces the emerging field as well as several of the core technologies that make it possible. We highlight the soaring needs for artistic content faced by the Entertainment and Design industries and how Creative AI is disrupting these industries by offering new applications to help augment and enhance human effort. We''ll outline how this is already happening today, giving several real world examples by Artomatix and Adobe, as well as offer insights into the future of this space.  Back
 
Keywords:
Game Development, Media and Entertainment, Video and Image Processing, GTC Europe 2017 - ID 23476
HPC and AI
Presentation
Media
Multi GPU Programming Models
Jiri Kraus (NVIDIA)
Do you need to compute larger or faster than a single GPU allows you to? Then come to this session and learn how to scale your application to multiple GPUs. In this session, you will learn how to use the different available multi GPU programming ...Read More

Do you need to compute larger or faster than a single GPU allows you to? Then come to this session and learn how to scale your application to multiple GPUs. In this session, you will learn how to use the different available multi GPU programming models and what are their individual advantages. All programming models will be introduced using same example applying a domain decomposition strategy.

  Back
 
Keywords:
HPC and AI, Programming Languages, HPC and Supercomputing, GTC Europe 2017 - ID 23031
Download:
 
Minsky at Murex
Pierre SPATZ (MUREX)
Murex has been an early adopters of GPU for pricing and risk management of complex financial options. GPU adoption has generated performance boost of its software while reducing its usage cost. Each new generation of GPU has also shown the impor ...Read More

Murex has been an early adopters of GPU for pricing and risk management of complex financial options. GPU adoption has generated performance boost of its software while reducing its usage cost. Each new generation of GPU has also shown the importance of the necessary reshaping of the architecture of the software using its GPU accelerated analytics. Minsky featuring far better GPU memory bandwidth and GPU-CPU interconnect rase the bar even further. Murex will show how it has handled this new challenge for its business.

  Back
 
Keywords:
HPC and AI, Performance Optimization, GTC Europe 2017 - ID 23209
Download:
 
Improving Deep Learning scalability on HPE servers with NovuMind: GPU RDMA made easy
Bruno MONNET (HEWLETT PACKARD ENTERPRISE), Ren WU (NOVUMIND INC)
HPE Deep Learning solutions empower innovation at any scale, building on our purpose-built HPC systems and technologies solutions, applications and support services. Deep Learning demands massive amounts of computational power. Those computation ...Read More

HPE Deep Learning solutions empower innovation at any scale, building on our purpose-built HPC systems and technologies solutions, applications and support services. Deep Learning demands massive amounts of computational power. Those computation power usually involve heterogeneous computation resources, e.g., GPUs and InfiniBand as installed on HPE Apollo.   NovuMinds NovuForce system leveraging state of art technologies make the deployment and configuration procedure fast and smooth. NovuForce deep learning softwares within the docker image has been optimized for the latest technology like NVIDIA Pascal GPU and infiniband GPUDirect RDMA. This flexibility of the software, combined with the broad GPU servers in HPE portfolio, makes one of the most efficient and scalable solutions.

  Back
 
Keywords:
HPC and AI, Performance Optimization, Tools and Libraries, GTC Europe 2017 - ID 23250
Download:
 
Efficiently Combining MPI and GPU-enhanced Tasks Within a Large Scale Industrial Application
Cedric Augonnet (CEA/DAM)
Discover how we designed and optimized a highly-scalable dense solver to solve Maxwell equations on our GPU-powered supercomputer. After describing our industrial application and its heavy computation requirements, we detail how we modernized it ...Read More

Discover how we designed and optimized a highly-scalable dense solver to solve Maxwell equations on our GPU-powered supercomputer. After describing our industrial application and its heavy computation requirements, we detail how we modernized it with programmability concerns in mind. We show how we solved the challenge of tightly combining tasks with MPI, and illustrate how this scaled up to 50000 CPU cores, reaching 1.38 Petaflops. A focus is then given on the integration of GPUs in this model, along with a few implementation tricks to ensure truly asynchronous programming. Finally, after briefly detailing how we added hierarchical compression techniques into our distributed solver over CPUs, we describe how we plan to unlock the challenges that yet prevented porting it on GPUs.

  Back
 
Keywords:
HPC and AI, Performance Optimization, HPC and Supercomputing, GTC Europe 2017 - ID 23277
Download:
 
Texture Based 3-D Volume Segmentation on GPU Clusters: Application to Digital Rock Physics
Rached ABDELKHALEK (TOTAL), Noomane KESKES (TOTAL), Issam Said (NVIDIA)
We leverage NVIDIA GPUs for connected components labeling and image classification applied to Digital Rock Physics (DRP), to help characterize reservoir rocks and study their pore distributions. We show on this talk how NVIDIA GPUs helped us sat ...Read More

We leverage NVIDIA GPUs for connected components labeling and image classification applied to Digital Rock Physics (DRP), to help characterize reservoir rocks and study their pore distributions. We show on this talk how NVIDIA GPUs helped us satisfy strict real-time restrictions dictated by the imaging hardware used to scan the rock samples. We present a detailed description of the workflow from a DRP approach perspectives, our algorithm and optimization techniques and performance results on the latest NVIDIA GPU generations.

  Back
 
Keywords:
HPC and AI, HPC and Supercomputing, Video and Image Processing, GTC Europe 2017 - ID 23303
Download:
 
Using OpenMP and OpenACC standards for GPU on OpenPOWER: motivations and results
Gabriel Hautreux (GENCI)
In order to prepare the scientific communities, GENCI and its partners have set up a technology watch group and lead collaborations with vendors, relying on HPC experts and early adopted HPC solutions. The two main objectives are providing guida ...Read More

In order to prepare the scientific communities, GENCI and its partners have set up a technology watch group and lead collaborations with vendors, relying on HPC experts and early adopted HPC solutions. The two main objectives are providing guidance and prepare the scientific communities to challenges of exascale architectures. The talk will present the OpenPOWER platform bought by GENCI and provided to the scientific community. Then, it will present the first results obtained on the platform for a set of about 15 applications using all the solutions provided to the users (CUDA,OpenACC,OpenMP,...). Finally, a presentation about one specific application will be made regarding its porting effort and techniques used for GPUs with both OpenACC and OpenMP.

  Back
 
Keywords:
HPC and AI, Performance Optimization, Programming Languages, GTC Europe 2017 - ID 23183
Download:
 
Movement is Key to VR: How Wireless-VR can boost enterprise applications
Nicole LAUX (SCHENKER TECHNOLOGIES)
Wireless-VR is widely defined as the key solution for maximum immersion. But why? Is it only the obvious reason of the omission of the heavy and inflexible cable? There is more behind it. Learn how the development of tracking technology goes han ...Read More

Wireless-VR is widely defined as the key solution for maximum immersion. But why? Is it only the obvious reason of the omission of the heavy and inflexible cable? There is more behind it. Learn how the development of tracking technology goes hand in hand with the increasing demand of Wireless-VR Hardware solutions, what hardware is out on the market now, what is coming and how can wireless solutions - whether standalone devices or Addons - create a higher value for your VR application? How large-scale location based VR and hardware manufacturers are expanding the boundaries of the VR industry, both for Entertainment and B2B?

  Back
 
Keywords:
HPC and AI, GTC Europe 2017 - ID 23388
Download:
 
Leadership Computing for Europe and the Path to Exascale Computing
Thomas SCHULTHESS (CSCS)
With over 5000 GPU-accelerated nodes, Piz Daint has been Europes leading supercomputing systems since 2013, and is currently one of the most performant and energy efficient supercomputers on the planet. It has been designed to optimize throughpu ...Read More

With over 5000 GPU-accelerated nodes, Piz Daint has been Europes leading supercomputing systems since 2013, and is currently one of the most performant and energy efficient supercomputers on the planet. It has been designed to optimize throughput of multiple applications, covering all aspects of the workflow, including data analysis and visualisation. We will discuss ongoing efforts to further integrate these extreme-scale compute and data services with infrastructure services of the cloud. As Tier-0 systems of PRACE, Piz Daint is accessible to all scientists in Europe and worldwide. It provides a baseline for future development of exascale computing. We will present a strategy for developing exascale computing technologies in domains such as weather and climate or materials science.

  Back
 
Keywords:
HPC and AI, GTC Europe 2017 - ID 23429
Download:
 
Inside the Volta GPU Architecture and CUDA 9
Axel KOEHLER (NVIDIA)
The presentation will give an overview about the new NVIDIA Volta GPU architecture and the latest CUDA 9 release. The NVIDIA Volta architecture powers the worlds most advanced data center GPU for AI, HPC, and Graphics. Volta features a new Strea ...Read More

The presentation will give an overview about the new NVIDIA Volta GPU architecture and the latest CUDA 9 release. The NVIDIA Volta architecture powers the worlds most advanced data center GPU for AI, HPC, and Graphics. Volta features a new Streaming Multiprocessor (SM) architecture and includes enhanced features like NVLINK2 and the Multi-Process Service (MPS) that delivers major improvements in performance, energy efficiency, and ease of programmability. New features like Independent Thread Scheduling and the Tensor Cores enable Volta to simultaneously deliver the fastest and most accessible performance. CUDA is NVIDIA''s parallel computing platform and programming model. You''ll learn about new programming model enhancements and performance improvements in the latest CUDA9 release.

  Back
 
Keywords:
HPC and AI, Programming Languages, Tools and Libraries, GTC Europe 2017 - ID 23434
Download:
In-Situ and Scientific Visualization
Presentation
Media
Virtual Reality for Scientific Visualisation
Christoph Anthes (UNIVERSITY OF APPLIED SCIENCES UPPER AUSTRIA)
This talk will give an introduction on the use of VR to enhance the understanding of Scientific Visualisation. Different application scenarios from hydro-meteorology, zoology, genetics and geophysics will be introduced in this talk and the benef ...Read More

This talk will give an introduction on the use of VR to enhance the understanding of Scientific Visualisation. Different application scenarios from hydro-meteorology, zoology, genetics and geophysics will be introduced in this talk and the benefits of VR technology in their specific application context will be explained. An outlook showing industrial use cases working with Mixed Reality technology will be given.

  Back
 
Keywords:
In-Situ and Scientific Visualization, Real-Time Graphics, HPC and Supercomputing, GTC Europe 2017 - ID 23389
Download:
Intelligent Machines and IoT
Presentation
Media
Finding your Voice in the Regulatory Age
Nigel CANNINGS (INTELLIGENT VOICE)
In contrast to demands for less regulation in the US, European financial institutions face new MiFID II and GDPR regulations which fundamentally affect how records are stored, retrieved and destroyed. 50% of all corporate data will have a voice ...Read More

In contrast to demands for less regulation in the US, European financial institutions face new MiFID II and GDPR regulations which fundamentally affect how records are stored, retrieved and destroyed. 50% of all corporate data will have a voice component in the next 5 years, which implies that companies not only need to know where data is being held, but also what is being said in it, and who is saying it. Part of this talk will showcase the solution produced by Telefonica/O2 and Intelligent Voice to capture, index and analyse mobile phone calls, and introduce them as part of a compliance and monitoring workflow for MiFID II. We will also show how machine learning can be applied to analysing real-time voice conversations to help spot fraud to an accuracy level on a par with humans

  Back
 
Keywords:
Intelligent Machines and IoT, Signal and Audio Processing, GTC Europe 2017 - ID 23379
Download:
 
The Intelligent Cardiovascular Ultrasound Scanner
Erik STEEN (GE HEALTHCARE)
GEHC introduced the Vivid E95 premium cardiovascular ultrasound scanner in June 2015 based on the ground breaking cSound system architecture. The Vivid E95 uses two Quadro GPUs for real time image reconstruction, image processing and visualizati ...Read More

GEHC introduced the Vivid E95 premium cardiovascular ultrasound scanner in June 2015 based on the ground breaking cSound system architecture. The Vivid E95 uses two Quadro GPUs for real time image reconstruction, image processing and visualization. The session will first give a quick introduction to the architecture and the clinical benefits. It will then cover new GPU based features that were recently introduced to further improve the performance and usability of the Vivid E95. Finally the session will cover future plans for making the scanner more intelligent with use of deep learning algorithms and initial results of using TensorRT for real time cardiac view detection will be shared

  Back
 
Keywords:
Intelligent Machines and IoT, Medical Imaging and Radiology, GTC Europe 2017 - ID 23440
Download:
Intelligent Video Analytics and Smart Cities
Presentation
Media
Real Time Video & Driver ID Verification from Vehicles
Manuel MAGALHAES (DIGITAL BARRIERS), Steven Harris (DIGITAL BARRIERS)
Leveraging NatSec technology to make real-time video streaming from vehicles possible, zero-latency, secure and affordable; and applying the latest generation of FaceRec analytics to ensure only authorised people are behind the wheel. ...Read More

Leveraging NatSec technology to make real-time video streaming from vehicles possible, zero-latency, secure and affordable; and applying the latest generation of FaceRec analytics to ensure only authorised people are behind the wheel.

  Back
 
Keywords:
Intelligent Video Analytics and Smart Cities, Self-Driving Cars, Video and Image Processing, GTC Europe 2017 - ID 23155
Download:
 
Radically Faster Video Intelligence: Using Deep Learning to help Police find People of Interest in Big Video Data
Henry HYDE-THOMSON (SEEQUESTOR)
SeeQuestor uses Deep Learning and Affordable Supercomputers to provide Radically Faster Video Intelligence to Police and Law Enforcement Agencies who need to search 100s or 1,000s of hours of CCTV or other video data as part of a criminal invest ...Read More

SeeQuestor uses Deep Learning and Affordable Supercomputers to provide Radically Faster Video Intelligence to Police and Law Enforcement Agencies who need to search 100s or 1,000s of hours of CCTV or other video data as part of a criminal investigation or a search for a missing person. Developed with input from the Met Police and the British Transport Police, SeeQuestor is now in use by law enforcement agencies around the world. This session will focus on the technology used (Deep Learning and Affordable Super Computers, powered by GPUs), the academic pedigree (two leading computer vision research groups from the UK), and illustrate the capabilities of the SeeQuestor platform with examples drawn from real use cases.

  Back
 
Keywords:
Intelligent Video Analytics and Smart Cities, Video and Image Processing, GTC Europe 2017 - ID 23492
Download:
Large Scale and Multi-Display Visualization
Presentation
Media
From Large-scale, Collaborative Multi-user VR to Cloud Streamed Car Configurator
Martin Rademacher (AUDI AG), Thomas ORENZ (AUDI AG)
VR-systems are fundamental tools for Audis internal product development process. Despite the fact that VR has been used for product evaluation for many years, physical models havent been completely replaced. Therefore, deficits of current VR-sys ...Read More

VR-systems are fundamental tools for Audis internal product development process. Despite the fact that VR has been used for product evaluation for many years, physical models havent been completely replaced. Therefore, deficits of current VR-systems have to be resolved. So, we introduce a new large-scale multi-user VR system, which could improve the confidence in internal evaluations performed in VR. Furthermore, Audi is using VR for retail gaining upselling potential called Walking VR and Sitting VR. See our approach bringing same highly complex and fully configurable 3D content into the cloud directly streamed to a customer under usage of a game engine. See how this gets measured and offering a significant upselling potential plus some examples of stunning visual real-time quality.

  Back
 
Keywords:
Large Scale and Multi-Display Visualization, Rendering and Ray Tracing, Real-Time Graphics, GTC Europe 2017 - ID 23441
Download:
 
Graphics Acceleration Is For All Modern Users
Tommy Stylsvig Würtz Rasmussen (HOLSTEBRO KOMMUNE)
Graphics acceleration is no longer something exclusively for engineers and 3D designers. With the release of Windows Server 2016, Windows 10, Office 2016 and a growing demand for a perfect multimedia experience when browsing, the everyday user d ...Read More

Graphics acceleration is no longer something exclusively for engineers and 3D designers. With the release of Windows Server 2016, Windows 10, Office 2016 and a growing demand for a perfect multimedia experience when browsing, the everyday user demand for graphics is growing as well. In this session you will hear how Holstebro Municipality, a Local Government located in the western part of Jutland in Denmark, implemented Nvidias GRID solution in their Citrix environment to be able to provide all of their users with the best graphical experience. As a side note they became able to virtualize the workload of their technical staff as well, leading to an even greater benefit and gain.

  Back
 
Keywords:
Large Scale and Multi-Display Visualization, Performance Optimization, GTC Europe 2017 - ID 23198
Download:
 
The power of integrated high-end visualization and VR in Product Design with 3DEXPERIENCE CATIA
Martin Leps (DASSAULT SYSTEMS)
Dassault Systemes is the worldwide PLM leader, its 3DEXPERIENCE platform being used to think, design and produce from the smallest objects to the most complex aerospace rockets or even full cities. The last R2017x version adds some major improvements ...Read More
Dassault Systemes is the worldwide PLM leader, its 3DEXPERIENCE platform being used to think, design and produce from the smallest objects to the most complex aerospace rockets or even full cities. The last R2017x version adds some major improvements on the graphics engine side. Leveraging native CAD or PLM data, designers are now able to use compelling texturing for life-like experience and review their design in VR without any data transform required. The talk will explain and show how from early simulation and automatic design optimization through final design review, the full product journey and how VR natively running on the platform can let designer think, experience and validate their products before they even exist.  Back
 
Keywords:
Large Scale and Multi-Display Visualization, Rendering and Ray Tracing, Real-Time Graphics, GTC Europe 2017 - ID 23447
Media and Entertainment
Presentation
Media
Established Resources in Art and Music, New Realities in Performance
Fabio Buccheri (NOYS VR)
Many companies and brands are facing problems to implement their concepts into XR Projects. From 360 storytelling, to 3d audio, to interactive experiences, to virtual worlds, the game- and film industry already consists of a lot of experts in al ...Read More

Many companies and brands are facing problems to implement their concepts into XR Projects. From 360 storytelling, to 3d audio, to interactive experiences, to virtual worlds, the game- and film industry already consists of a lot of experts in all these areas. This talk will be about how NOYS VR are tackling these challenges by adapting established standards and combining them to new art & creation processes for this new medium. Although this example is based on the music, gaming entertainment industry, it shows how different industries can benefit from each other and monetize through innovative content while putting the customers into new and social realities.

  Back
 
Keywords:
Media and Entertainment, Real-Time Graphics, Video and Image Processing, GTC Europe 2017 - ID 23426
Download:
 
A Multi-GPU Scalable SDK for Real-time Stereo Stitching of 360 Video and Audio
Thomas TRUE (NVIDIA)
This session will introduce and provide an overview of the VRWorks Video 360 - NVIDIA''s implementation of a motion-flow-based, real-time, CUDA-accelerated , GPU-scalable, 360 Stereo Stitching SDK with support for both video and audio. We will go ove ...Read More
This session will introduce and provide an overview of the VRWorks Video 360 - NVIDIA''s implementation of a motion-flow-based, real-time, CUDA-accelerated , GPU-scalable, 360 Stereo Stitching SDK with support for both video and audio. We will go over the overall stitching pipeline, show example videos from different stereo rigs stitched using the SDK, describe the APIs, explain the process of writing sample apps using the SDK, and analyze the do''s-and-don''ts in obtaining a high-quality stitched output.  Back
 
Keywords:
Media and Entertainment, Virtual Reality and Augmented Reality, Video and Image Processing, GTC Europe 2017 - ID 23449
Download:
 
New High-speed Professional Video Compression using CUDA
Jan WEIGNER (CINEGY GMBH)
Video and image resolutions keep growing. It is UHD undefined 4K today and 8K has been announced. UHD is already a challenge for existing video and image compression algorithms that quickly overload the CPU. New GPU-based compression algorithms ...Read More

Video and image resolutions keep growing. It is UHD undefined 4K today and 8K has been announced. UHD is already a challenge for existing video and image compression algorithms that quickly overload the CPU. New GPU-based compression algorithms help overcome this by addressing the two main bottlenecks - CPU performance and the PCIe bus limitations. Cinegys DANIEL2 GPU video codec is a highly scalable CUDA-based video encoder and decoder (codec) for professional video editing, post-production and broadcast. It is also used large scale imaging (GIS, medical) and VR. Using a GPU-based video codec can increase performance twenty-fold compared to traditional CPU based approaches while at the same time offloading the CPU for other tasks. 8K video editing on a NVIDIA-based notebooks is real.

  Back
 
Keywords:
Media and Entertainment, Tools and Libraries, Video and Image Processing, GTC Europe 2017 - ID 23493
Download:
Medical Imaging and Radiology
Presentation
Media
cuDIMOT: A CUDA Toolbox for Modelling the Brain Tissue Microstructure from Diffusion MRI.
Moises Hernandez Fernandez (OXFORD CENTRE FOR FUNCTIONAL MRI OF THE BRAIN (FMRIB))
cuDIMOT (CUDA Diffusion Modelling Toolbox) is a toolbox for designing and fitting nonlinear models (non-only diffusion) on NVIDIA GPUs. It offers a friendly interface for implementing new models and it automatically generates parallel CUDA code. ...Read More

cuDIMOT (CUDA Diffusion Modelling Toolbox) is a toolbox for designing and fitting nonlinear models (non-only diffusion) on NVIDIA GPUs. It offers a friendly interface for implementing new models and it automatically generates parallel CUDA code. Various model-fitting approaches are available, including Grid Search, nonlinear Levenberg-Marquardt optimisation and Bayesian inference using MCMC. We present how cuDIMOT has been developed and is being used in the context of diffusion MRI for studying brain tissue microstructure. The toolbox achieves accelerations of two orders of magnitude using a single K80 NVIDIA device compared to the commonly used CPU tools. Large projects such as the UK Biobank, an epidemiological study scanning 100,000 subjects, will tremendously benefit from this toolbox.

  Back
 
Keywords:
Medical Imaging and Radiology, Performance Optimization, Tools and Libraries, GTC Europe 2017 - ID 23165
Download:
 
Localization in 3D Biomedical Image Data Using Deep Learning
Mark-Jan Harte (AIDENCE)
We discuss two deep neural networks that aid radiologists with the localisation of anomalies in biomedical volumes. Our first application concerns the detection of lung nodules on CT chest scans. Secondly, we designed a network that localises th ...Read More

We discuss two deep neural networks that aid radiologists with the localisation of anomalies in biomedical volumes. Our first application concerns the detection of lung nodules on CT chest scans. Secondly, we designed a network that localises the neural foramina on MRI lumbar spine scans. Both applications require a tremendous amount of computational power as the input data is in 3D. In our talk, we explain and compare these two networks and their performance. Moreover, we discuss some of the practical problems that arise when designing neural networks for medical image analysis.

  Back
 
Keywords:
Medical Imaging and Radiology, GTC Europe 2017 - ID 23301
Download:
 
Deep Learning in Healthcare
Bram Van Ginneken (RADBOUDUMC)
Deep learning has become the most powerful driver in medical image analysis. In this talk, I provide an overview of these recent developments, with a focus on results of recent competitions in radiology, pathology, and ophthalmology. I show how ...Read More

Deep learning has become the most powerful driver in medical image analysis. In this talk, I provide an overview of these recent developments, with a focus on results of recent competitions in radiology, pathology, and ophthalmology. I show how detection of lung cancer with CT can be improved with deep learning, as shown in the LUNA16 challenge and the Kaggle Data Science Bowl of 2017. The CAMELYON16 and CAMELYON17 challenges have shown that deep networks outperform pathologist at the detection of lymph node metastases of breast cancer. Finally, in ophthalmology, early detection of diabetic retinopathy with convolutional networks has shown excellent results. These developments will have a major impact on healthcare.

  Back
 
Keywords:
Medical Imaging and Radiology, Video and Image Processing, GTC Europe 2017 - ID 23207
Download:
 
How To Predict ICU Mortality with Digital Health Data
Max Pumperla (SKYMIND)
In this presentation, we will discuss modeling electronic health record (EHR) data with deep learning and Deeplearning4j We describe how to train an long short-term memory recurrent neural network (LSTM RNN) to predict in-hospital mortality amon ...Read More

In this presentation, we will discuss modeling electronic health record (EHR) data with deep learning and Deeplearning4j We describe how to train an long short-term memory recurrent neural network (LSTM RNN) to predict in-hospital mortality among patients hospitalized in the intensive care unit (ICU). Of particular note, our results show that even for a dataset of moderate size, the LSTM is competitive with alternative approaches, including decision trees and multilayer perceptrons, using hand-engineering features. We will also show how to parallelize model training on a Spark cluster. Finally, we will highlight potential extensions of this work and other use cases for EHR data and deep learning. All code and data are publicly available so that attendees may reproduce our work.

  Back
 
Keywords:
Medical Imaging and Radiology, Tools and Libraries, Video and Image Processing, GTC Europe 2017 - ID 23239
Download:
Other
Presentation
Media
Acceleration of Monte Carlo Simulation for American Option Pricing
Wojciech Michal PAWLAK (SIMCORP/UNIVERSITY OF COPENHAGEN)
Current results of GPU acceleration efforts targeting financial algorithms are focused around Monte Carlo simulations for pricing of American options using a custom localized implementation Longstaff-Schwartz (2001) algorithm that allows for exp ...Read More

Current results of GPU acceleration efforts targeting financial algorithms are focused around Monte Carlo simulations for pricing of American options using a custom localized implementation Longstaff-Schwartz (2001) algorithm that allows for exposing more parallelism. We sketch the necessary theory and present the employed CUDA parallelization strategy as well as summary of test executions. Currently achieved results are satisfactory and give a motivation for further optimization improvements and algorithmic adjustments. This work is an integral part of Wojciechs Ph.D. research project as well as one of SimCorp Technology Labs innovation goals.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID P23054
 
ReVolVR - Rendering Volume Data in VR using HTC Vive
Ingrid SCHOLL (FH AACHEN)
ReVolVR is a new Virtual Reality (VR) volume rendering application based on the HTC Vive VR technique. The application uses the ray casting algorithm for direct volume rendering. Ray casting needs a transfer function to classify several surfaces ...Read More

ReVolVR is a new Virtual Reality (VR) volume rendering application based on the HTC Vive VR technique. The application uses the ray casting algorithm for direct volume rendering. Ray casting needs a transfer function to classify several surfaces. To find a good transfer function is in general a manual and time-consuming procedure and requires detailed knowledge of the data. With ReVolVr, the transfer function can be modified in the virtual scene while continuously real-time rendering the stereoscopic 3D volume through GPU-based ray casting shader. All interactions are designed to conveniently reflect to real movements of the user.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID P23055
 
Towards CFD at Exascale: Hybrid MulticoreundefinedManycore Massively Parallel High-Order Navier-Stokes Solver
Hadi ZOLFAGHARI (UNIVERSITY OF BERN)
A GPU-accelerated high-order massively-parallel 3D Navier-Stokes solver has been developed for heart valve simulation. It is optimized for a Cray XC50 supercomputer by distributing the workload to different MPI processes and by offloading double ...Read More

A GPU-accelerated high-order massively-parallel 3D Navier-Stokes solver has been developed for heart valve simulation. It is optimized for a Cray XC50 supercomputer by distributing the workload to different MPI processes and by offloading double-precision kernels to GPUs. The GPU kernels are written in CUDA C and are called by the FORTRAN legacy code. For a high-order finite-difference gradient kernel speedups of 5x (Tesla K20x) and 20x (Tesla P100) were achieved. In combination with 16 MPI threads on a single node of the Cray XC50, a peak speedup of 33x was achieved using CUDA MPS. Similar performance was also achieved for other differential operators, demonstrating the potential of GPU technology for bringing biomedical CFD to exascale computing.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID P23060
 
Computation of Diffracted Wavefields below Levant Basin Multi-layered Evaporitic Succession on GPUs
Nikolay ZYATKOV (NOVOSIBIRSK STATE UNIVERSITY)
Across the Mediterranean basins, the Messinian salinity crisis resulted in the deposition of up to 2 km thick multi-layered evaporitic succession consisting of alternating layers of halite and clastics. Such geological objects obscure seismic im ...Read More

Across the Mediterranean basins, the Messinian salinity crisis resulted in the deposition of up to 2 km thick multi-layered evaporitic succession consisting of alternating layers of halite and clastics. Such geological objects obscure seismic imaging and may even be over pressurized posing potential drilling hazards, which are often hard to predict. We demonstrate TPDOT&TWSM approach developed in IPGG SB RAS by example of evaluating the interference wavefields wave fragment into the shadow zone for real geological case from the Levant Basin, offshore Israel. Using of GPUs allowed accelerating TWSM algorithm based on multiple large size matrix-vector operations in hundreds and more times.

  Back
 
Keywords:
Other, Other, GTC Europe 2017 - ID P23046
Download:
 
Deep ECG Classification System
Boris Pyakillya (NTR LAB)
 
Keywords:
Other, Other, Signal and Audio Processing, GTC Europe 2017 - ID P23035
 
Why Light Field Technology is Essential for the Progression of Augmented and Mixed Reality
Andy GSTOLL (AVEGANT)
The adoption of augmented and mixed reality is being held back for a simple reason: no solution exists to see virtual objects at an arms length. Light field displays change this by revolutionizing the optical architectures for augmented and mixed re ...Read More
The adoption of augmented and mixed reality is being held back for a simple reason: no solution exists to see virtual objects at an arms length. Light field displays change this by revolutionizing the optical architectures for augmented and mixed reality solutions. In this talk, Andy Gstoll will discuss the merits and drawbacks of light field technologies including sections on multi-focal imagery and near-field image generation. A look at the current state of the art will follow, concluded by details on the light field solution employed by Avegant and its potential for the future.  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23342
Download:
 
The Role of GPUs in Geovisualisation
Todd MOSTAK (MAPD)
Todd will explore the topic of GPUs & their role in geovisualisation. In particular, attendees will hear about how complex visualisations with massive amounts of geospatial data are an ideal match for GPUs, unlocking extreme speeds for interactiv ...Read More
Todd will explore the topic of GPUs & their role in geovisualisation. In particular, attendees will hear about how complex visualisations with massive amounts of geospatial data are an ideal match for GPUs, unlocking extreme speeds for interactive data exploration and real-time insight generation. The ability to instantly interact with billions of rows of geospatial data can be used across industries such as ad tech, energy, financial services, government, retail and service providers, allowing them to quickly find anomalies and drill-down into the individual level without pre-aggregating or downsampling.  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23345
Download:
 
The Future of IoT and intelligent Applications
Enzo FENOGLIO (CISCO)
Machine learning and deep learning applications are revolutionizing how we as consumers interact with our compute devices by imbuing them with speech recognition, machine vision, and other perceptual capabilities. We are now seeing new advanceme ...Read More

Machine learning and deep learning applications are revolutionizing how we as consumers interact with our compute devices by imbuing them with speech recognition, machine vision, and other perceptual capabilities. We are now seeing new advancements in AI which move from simple pattern recognition and sensory data processing to much deeper semantic processing. These new advancements in essence bridge the gap between machine learning techniques, including commoditized deep learning on SIMD GPUs , and the next generation of specialized distributed-memory MIMD hardware for large-scale graph analysis for symbolic artificial intelligence. In this session we will cover the new capabilities and use cases Cisco is targeting with this new breakthrough technology.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23346
Download:
 
How GPUs Enable XVA Pricing and Risk Calculations for Risk Aggregation
James Mesney (KINETICA)
Get the latest information on how financial markets are using advanced in-database analytics for real-time risk aggregation. Advanced in-database analytics allows the bank to run custom XVA algorithms at scale with the GPUs massive parallelizati ...Read More

Get the latest information on how financial markets are using advanced in-database analytics for real-time risk aggregation. Advanced in-database analytics allows the bank to run custom XVA algorithms at scale with the GPUs massive parallelization. This approach allows banks to move counterparty risk analysis from batchundefinedovernight to a streamingundefinedreal-time system for flexible real-time monitoring by traders, auditors, and management. Real-world examples and insights will be provided, including how a multinational bank is using Kinetica as a real-time risk modeling engine running on public cloud-based, Microsoft Azure GPU instances. The bank can now handle time-sensitive, compute-intensive risk computations to project years into the future across hundreds of variables.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23383
Download:
 
Developing & Deploying Autonomous Driving Applications with the NVIDIA DRIVE PX Platform
Shri SUNDARAM (NVIDIA), Tom TOMAZIN (NVIDIA)
This session will cover how to use NVIDIA DRIVE PX to build a self-driving vehicle, including insights into data acquisition, data annotation, neural network training, and in-vehicle inference. In addition, it will focus on how DRIVE PX delivers ...Read More

This session will cover how to use NVIDIA DRIVE PX to build a self-driving vehicle, including insights into data acquisition, data annotation, neural network training, and in-vehicle inference. In addition, it will focus on how DRIVE PX delivers the performance, energy-efficiency and safety requirements for it to be brain of production autonomous vehicles.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23452
Download:
 
Efficient Training & Testing of ADAS AI with synthetic data
Rodolphe TCHALEKIAN (ESI GROUP)
Massive amounts of labeled and unlabeled datasets are needed both for training autonomous vehicles to navigate complex and unexpected driving scenarios, and to evaluate that training. As a substitute for hours of recorded data, Pro-SiVIC creates ...Read More

Massive amounts of labeled and unlabeled datasets are needed both for training autonomous vehicles to navigate complex and unexpected driving scenarios, and to evaluate that training. As a substitute for hours of recorded data, Pro-SiVIC creates synthetic data to simulate the output from multiple sensor systems for outdoor scenarios that combine vehicles, obstacles, pedestrians, weather, and road conditions. We will demonstrate how powerful and efficient parallel computing with NVIDIA Drive PX2 can be used with Pro-SiVIC synthetic data to process that data in real time. We will compare the performance of a trained lane detection algorithm, running on Drive PX2, against a 3D Pro-SiVIC scene with simulated raw camera data, and a real video recorded from a car in similar conditions.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23475
Download:
 
Emergency Response with Deep Neural Networks and Satellite Imagery
Damian BORTH (GERMAN RESEARCH CENTER FOR ARTIFICIAL INTELLIGENCE), Benjamin BISCHKE (TECHNICAL UNIVERSITY OF KAISERSLAUTERN)
Recent advances in earth observation are opening up a new exciting area for exploration of satellite image data. In this session you will learn how to analyse this new data source with deep neural networks. Focusing on Emergency Response, you wi ...Read More

Recent advances in earth observation are opening up a new exciting area for exploration of satellite image data. In this session you will learn how to analyse this new data source with deep neural networks. Focusing on Emergency Response, you will learn (1) how to apply deep neural networks for Semantic Segmentation on satellite imagery. Additionally, we present recent advances of the Multimedia Satellite Task at MediaEval 2017 and show (2) how to extract and fuse content of natural disasters from Satellite Imagery and Social Media Streams. It is assumed that registrants are already familiar with fundamentals of deep neural networks.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23479
Download:
 
Earth Observation: Land Use and Land Cover Classification Using Satellite Images
Patrick HELBER (UNIVERSITY OF KAISERSLAUTERN)
We address the challenge of land use and land cover classification using remote sensing satellite images. For this challenging task, we use the openly and freely accessible Sentinel-2 satellite images. Our novel dataset covers 13 different spectral b ...Read More
We address the challenge of land use and land cover classification using remote sensing satellite images. For this challenging task, we use the openly and freely accessible Sentinel-2 satellite images. Our novel dataset covers 13 different spectral bands and consists of 27,000 labeled images. We present an evaluation of this dataset using deep Convolutional Neural Networks (CNN). In addition, we compare our results to existing benchmark datasets. With the proposed new dataset, we achieved an overall accuracy of 98.57%. We demonstrate how the classification system can be used for detecting land use and land cover changes and how it can assist in improving geographical maps.  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23480
Download:
 
The Core in Financial Systems: Legal Entity Identifier and its Linkage to other Systems
Alexander ARIMOND (SOCIOVESTIX LABS LTD.)
With globalization companies have come to operate in networks spanning countries, continents, and most importantly, legal jurisdictions. Unfortunately, financial markets struggle to provide the transparency for complex ownership relationships of glob ...Read More
With globalization companies have come to operate in networks spanning countries, continents, and most importantly, legal jurisdictions. Unfortunately, financial markets struggle to provide the transparency for complex ownership relationships of global corporations. A core element to improve transparency are Legal Entity Identifier (LEI), a global and open standard for the identification of legal entities. However, an important first step towards full utilization of LEIs is their linkage into legacy identification systems such as BIC or ISIN. This talk will present work in the area of data record linkage with LEIs and BICs data record files. It will show how a combination of distance metrics and crowdsourcing can provide a robust fusion of both datasets.  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23481
 
Radiomics : The Path to Personalized Medicine
Klaus MAIER-HEIN (GERMAN CANCER RESEARCH CENTER)
Medical images uniquely represent the anatomical and functional progress of diseases in 3D space and time. Radiomics denotes the emerging endeavor of systematic extraction, mining and leveraging of this rich information towards personalized medi ...Read More

Medical images uniquely represent the anatomical and functional progress of diseases in 3D space and time. Radiomics denotes the emerging endeavor of systematic extraction, mining and leveraging of this rich information towards personalized medicine. We aim to comprehensively summarize imaging information from multiple time-points and modalities in condensed, quantitative signatures and link them with clinical and biological parameters (e.g. genomics or proteomics). We develop our methods for various clinical applications, with a particular emphasis on prostate cancer, breast cancer and brain tumors. The talk will introduce these developments with a particular focus on the machine learning aspects and big data applications where large-scale heterogeneous data sources are analyzed.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23482
Download:
 
AI is your Business - Translating Hype into Action
Paul BROOK (DELL EMC), Bernhard OTUPAL (DELL EMC)
Artificial Intelligence the next big thing, disruptive, vital, innovative, dangerous, saving grace, ubiquitous, unavoidable, engine to future growth, a privacy nightmare? It can be everything, but can it be nothing? Competitive advantage require ...Read More

Artificial Intelligence the next big thing, disruptive, vital, innovative, dangerous, saving grace, ubiquitous, unavoidable, engine to future growth, a privacy nightmare? It can be everything, but can it be nothing? Competitive advantage requires it. An insecure, turbulent world demands it. What is your strategy on AI? At the forefront of innovation, a follower, wait and see? This session will attempt to peel back the layers of complexity around AI and introduce a conceptual framework around establishing an AI strategy for your business one that starts where it needs to and scales naturally from the development phase through to full implementation.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23486
Download:
 
Nutanix AHv & NVIDIA: Putting the V in vGPU!
John Elie ARAMAN (NUTANIX SERVICES)
The combination of Nutanix AHV and NVIDIA brings out the best in your graphical applications, VDI environments or 3D applications. Come join the session and learn how the Nutanix Enterprise Cloud Platform drives performance, efficiency and agili ...Read More

The combination of Nutanix AHV and NVIDIA brings out the best in your graphical applications, VDI environments or 3D applications. Come join the session and learn how the Nutanix Enterprise Cloud Platform drives performance, efficiency and agility for your virtualized applications.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23490
Download:
 
VR for Professionals - Introducing the first commercial VR wearable high performance platform
Gwen COBLE (HP, INC.)
Gwen will explain HPs Vision on Commercial VR space and how HP is approaching it today . HP's commercial VR strategy objective is to deliver the best and most immersive VR and compute experience and offer end to end solutions. All this will ...Read More

Gwen will explain HPs Vision on Commercial VR space and how HP is approaching it today . HP's commercial VR strategy objective is to deliver the best and most immersive VR and compute experience and offer end to end solutions. All this will then translate into optimizing their investment and cut costs for commercial customers. She will also deep dive into the Z VR Backpack, the first wearable and untethered VR PC.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23495
Download:
 
Explore ProVR & the wider real-world benefits to your industry. Powered by Lenovo Workstations
Mike LEACH (LENOVO), Joerg WALTHER (LENOVO)
While the technology has been around for 20 years, the professional use of VR is nothing new; however with advanced graphics technologies from NVIDIA and the latest Lenovo computer workstations it is now possible to deliver real-world return on ...Read More

While the technology has been around for 20 years, the professional use of VR is nothing new; however with advanced graphics technologies from NVIDIA and the latest Lenovo computer workstations it is now possible to deliver real-world return on investment without the multi-million dollar price tag of just a few years ago. Use VR at every stage of your business and utilize game-changing implementations of AR and VR to take workflows within manufacturing to new heights; stream lining and speeding up production processes, saving both time money and resources. We will be presenting our global VR Strategy, some typical industry references and VR demos using the latest high performance ThinkStation & ThinkPad workstations; powered by NVIDIA VR Ready graphics to deliver the best VR experiences.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23500
Download:
 
GPUs in the Cloud and why should I care?
Andreas POHL (MICROSOFT)
Today GPUs are used in many different industries to solve different Problems, from AI over Deep learning to Mixed reality. In this session you will learn about the industry use cases and how the partnership of Microsoft and NVIDIA is enabling yo ...Read More

Today GPUs are used in many different industries to solve different Problems, from AI over Deep learning to Mixed reality. In this session you will learn about the industry use cases and how the partnership of Microsoft and NVIDIA is enabling your digital transformation. We will define what Mixed Reality is and what you can learn from Game Developers creating visual high-quality content for this platform with the help of Azure and NVIDIA GPUs. And we will share with you how you can engage with industry experts from Microsoft and NVIDIA to help you to transform your Business.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23502
Download:
 
Delivering a Transformational 3D Graphics User Experience with VMware Horizon, Blast Extreme Accelerated Transport, and NVIDIA GRID
Sebastian BRAND (VMWARE), Luke WIGNALL (NVIDIA)
During this session, attendees will discover the benefits of virtualising any desktop or application using VMware Horizon. ...Read More

During this session, attendees will discover the benefits of virtualising any desktop or application using VMware Horizon.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23042
Download:
 
Operationalizing Machine Learning Using GPU Accelerated, In-Database Analytics
Matthew Hawkins (KINETICA)
Often organizations have custom algorithms, functions, and libraries for sophisticated analytics on large datasets. Data scientists use machine learning and deep learning libraries such as TensorFlow, Caffe, and Torch to gain better insights. Operati ...Read More
Often organizations have custom algorithms, functions, and libraries for sophisticated analytics on large datasets. Data scientists use machine learning and deep learning libraries such as TensorFlow, Caffe, and Torch to gain better insights. Operationalizing these libraries and advanced analytics can be challenging, given the data pipeline, repeatable processes, and lack of persistence for output of the algorithm. Attendees will learn how they can leverage the parallel processing power of a GPU-accelerated database to bridge the gap between data science, data analytics, and business intelligence, and how GPUs are well-suited for the types of vector and matrix operations found in machine learning and deep learning systems.  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23071
Download:
 
GDPR Discovery Using Text Mining and Deep Learning
Ari Juntunen (ELINAR)
EU new privacy regulation requires all companies to understand what personal information they hold about EU citizens and they need consent from each person to keep holding such information. In this session we learn how to apply Deep Learning on ...Read More

EU new privacy regulation requires all companies to understand what personal information they hold about EU citizens and they need consent from each person to keep holding such information. In this session we learn how to apply Deep Learning on content (i.e. documents and records) to enable efficient GDPR discovery. Elinar has built repeatable AI based solution that uses NVidia GPUs for per customer learning and inferencing workloads. This session will cover common challenges for building discovery pipeline and guidance on how to scale the solution for high volumes.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23120
Download:
 
Introducing NVIDIA Holodeck
David Weinstein (NVIDIA)
Bring your ideas to life with NVIDIA Holodeck, the worlds first intelligent, photorealistic, and collaborative virtual reality platform. With Holodeck designers will be able to visualize large, highly detailed models and explore them in photo-re ...Read More

Bring your ideas to life with NVIDIA Holodeck, the worlds first intelligent, photorealistic, and collaborative virtual reality platform. With Holodeck designers will be able to visualize large, highly detailed models and explore them in photo-real fidelity in real-time. Design teams can collaborate on these complex models remotely to discover new ideas, streamline reviews, and minimize costly physical prototyping. Holodeck even promises to tap into AI to accelerate design workflows and complex simulations. Come hear the talk and then experience Holodeck demos in the VR Village!

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23192
Download:
 
Human Agency in the Robotic Age
Alexander Mankowsky (DAIMLER AG)
AI systems are all the rage, autonomous cars and cooperative robots seem to be around the corner. However, in the open field of public life we need to design these artifacts in a way that people can not only interact, but cooperate with them. In ...Read More

AI systems are all the rage, autonomous cars and cooperative robots seem to be around the corner. However, in the open field of public life we need to design these artifacts in a way that people can not only interact, but cooperate with them. In this talk, the concept of Informed Trust will be discussed as a model to enable a joyful and safe cooperation between men and machine.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23021
Download:
 
Baidu Apollo & Autonomous Driving
Weihao Gu (BAIDU)
Baidu Apollo & Autonomous Driving ...Read More
Baidu Apollo & Autonomous Driving  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23344
Download:
 
Machine Learning and Artificial Intelligence at Mercedes-Benz
Kal MOS (MERCEDES-BENZ)
We are already surrounded by intelligence-based user experience such as home AI digital assistants, smartphones that provide suggested actions and contents, shopping bots that propose items to buy based of shopping patterns, etc. Interactions wi ...Read More

We are already surrounded by intelligence-based user experience such as home AI digital assistants, smartphones that provide suggested actions and contents, shopping bots that propose items to buy based of shopping patterns, etc. Interactions with machines around us are quickly becoming the norm. In-vehicle user experience needs intelligence not only to delight the user with a truly personalized experience and to simplify repetitive actions but also to minimize cognitive load and to decrease driver distraction. The latest Mercedes-Benz head-unit was designed and build with this demand in its DNA. Driver behavior and interactions are analyses in real-time to predict what the driver will do next, using machine learning algorithms developed in-house.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23353
Download:
 
An Energy-Efficient Parallel Algorithm for Real-Time Near-Optimal UAV Path Planning
Daniele Palossi (ETH ZÜRICH)
Path planning is one of the key functional blocks for autonomous vehicles constantly updating their route in real-time. In this talk we present the main ideas behind our energy-efficient, parallel, nearoptimal path planner. Approximate path comp ...Read More

Path planning is one of the key functional blocks for autonomous vehicles constantly updating their route in real-time. In this talk we present the main ideas behind our energy-efficient, parallel, nearoptimal path planner. Approximate path computation has proven a promising approach to reduce total execution time, at the cost of a slight loss in accuracy. Due to the fusion of environmental information with the kinematics of the vehicle, the safety of the mission is always guaranteed despite the non-optimality of the path. Furthermore, we show how we can ensure efficient use of embedded GPU resources (NVidia Tegra X1), through program transformations. Lastly, we introduce the predictable execution model (PREM) and its potentiality when applied to our planner.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23356
Download:
 
Accelerating common Business Software with the Power of GPUs & Deep Learning
Dieter Weiler (Q2WEB GMBH), Lison WEILER (SHARERADO UG)
In a world of ever growing amounts of data lakes and an urgent need to make use of them and gain contextually relevant information out of them, the importance of being able to analyze them in real-time is greater than it ever has been before. However ...Read More
In a world of ever growing amounts of data lakes and an urgent need to make use of them and gain contextually relevant information out of them, the importance of being able to analyze them in real-time is greater than it ever has been before. However, we have seen, that companies are marked by immense waiting times for queries and the struggle to extract value from their datasets, when they use traditional solutions. We will elaborate on how we have solved these problems in the telco industry by accelerating all parts of the analysis with the power of GPUs while having an easy migration path. Moreover, we will discuss how AI & Deep Learning can be used to make existing applications more intelligent.  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23358
Download:
 
Re-Inventing the Scientific Method: How Artificial Intelligence is Revolutionising Drug Discovery
Dean PLUMBLEY (BENEVOLENT AI)
Re-Inventing the Scientific Method: How Artificial Intelligence is Revolutionising Drug Discovery Despite the huge growth of knowledge and information, the process of scientific discovery has not changed for 50 years.? In drug discovery, the cur ...Read More

Re-Inventing the Scientific Method: How Artificial Intelligence is Revolutionising Drug Discovery Despite the huge growth of knowledge and information, the process of scientific discovery has not changed for 50 years.? In drug discovery, the current system is not working health systems and services around the world are failing and developing medicines is still a very lengthy, risky and expensive process with the cost of developing a new drug conservatively estimated at $1bn with less than 1 in 10 drugs entering the clinic making it to market. Re-Inventing the Scientific Method: How Artificial Intelligence is Revolutionising Drug Discovery

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23364
Download:
 
How AI Revolutionizes Data & Document Management
Florian Kuhlmann (LEVERTON)
LEVERTON develops and applies deep learning technology to extract, structure and manage data from corporate documents in more than 20 languages. Learn how we leverage deep learning and NLP to solve problems of Optical Character Recognition (OCR) ...Read More

LEVERTON develops and applies deep learning technology to extract, structure and manage data from corporate documents in more than 20 languages. Learn how we leverage deep learning and NLP to solve problems of Optical Character Recognition (OCR), Document Classification, and Information Extraction to turn unstructured documents into structured data. Through the application of AI technology, data quality can be improved, processes accelerated, and efficiencies increased significantly. Find out how global organizations in real estate, finance, accounting and law save time and money - powered by deep learning technology.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23384
Download:
 
What is Level 5 Autonomous Motorsport?
Bryn Balcombe (ROBORACE)
Roborace is the world''s first driverless electric racing series providing an extreme motorsport and entertainment platform for the future of road relevant technologies. This session will explore how the platform will help teams to devel ...Read More

Roborace is the world''s first driverless electric racing series providing an extreme motorsport and entertainment platform for the future of road relevant technologies. This session will explore how the platform will help teams to develop level 5 autonomous software that will one day make it to our roads by pushing it to the limits in extreme yet safe environments around the world.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23432
Download:
 
Enabling the Intelligent Enterprise
Markus NOGA (SAP)
For SAP, making all enterprise applications intelligent entails partnering with the best providers in the market. Learn how SAP and Nvidia join forces to enable digital business transformation and drive the delivery of disruptive machine learning cap ...Read More
For SAP, making all enterprise applications intelligent entails partnering with the best providers in the market. Learn how SAP and Nvidia join forces to enable digital business transformation and drive the delivery of disruptive machine learning capabilities and find out how they aim to establish a mainstream platform and infrastructure combination for deep learning implementation in enterprise applications.  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23473
Download:
 
Introduction to human-eye resolution VR
Urho KONTTORI (VARJO)
Varjo is redefining reality by jumpstarting a new era in computing. Our hardware and software lets you seamlessly mix realities together, moving from the real world to an extended reality and into pure virtual reality - all in human eye resolution. ...Read More
Varjo is redefining reality by jumpstarting a new era in computing. Our hardware and software lets you seamlessly mix realities together, moving from the real world to an extended reality and into pure virtual reality - all in human eye resolution. Varjos patented Bionic Display technology mimics the natural behaviour of the human eye and allows us to create products with up to 100 times the resolution of any of todays VRundefinedAR devices. This marks the beginning of the era of completely immersive computing. Join this talk to learn about how Varjo is redefining the human capabilities to create, work, learn and play by revolutionizing HMD design.  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23487
 
Sequence to Sequence Modeling: Neural Machine Translation with Sockeye
Cyrus VAHID (AMAZON WEB SERVICES)
NMT is often performed using sequence to sequence modeling, where the input is a sequence of variable length tensor representation of a sentence in source language , and the output is the another variable length tensor representation of target l ...Read More

NMT is often performed using sequence to sequence modeling, where the input is a sequence of variable length tensor representation of a sentence in source language , and the output is the another variable length tensor representation of target language. Sockeye project, a sequence-to-sequence framework for Neural Machine Translation based on Apache MXNet Incubating. It implements the well-known encoder-decoder architecture with attention. The talk covers LSTM networks, NMT fundamentals, an overview of how to use Sockeye for implementing translation tasks, and areas of active research for those who are interested in further study of the subject.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23496
Download:
 
Solutions and resources for building and supporting NVIDIA GRID, and Quadro vDWS, mixed version environments
Luke WIGNALL (NVIDIA), Sarah MANNION (NVIDIA)
As GRID and Quadro vDWS environments grow over time, the potential for mixed versions requires thoughtful planning and preparation. This session will explore customer use cases where various versions of GRID and Quadro vDWS are needed and presen ...Read More

As GRID and Quadro vDWS environments grow over time, the potential for mixed versions requires thoughtful planning and preparation. This session will explore customer use cases where various versions of GRID and Quadro vDWS are needed and present potential solutions for building and supporting these environments. Also covered will be the resources available to build and support your own mixed environment. Presenters will be offering an extended Q&A time to allow for discussion and to capture your questions and concerns.

  Back
 
Keywords:
Other, GTC Europe 2017 - ID 23498
Download:
Performance Optimization
Presentation
Media
High throughtput low latency data management using GPUDirect
An how to implement efficient data transfers between a FPGA-Based interconnect and a GPU running a Persistent Kernel (PK) in autonomous fashion. While PK provide the ability to handle continuous data stream without CPU involvement. Bringing cohe ...Read More

An how to implement efficient data transfers between a FPGA-Based interconnect and a GPU running a Persistent Kernel (PK) in autonomous fashion. While PK provide the ability to handle continuous data stream without CPU involvement. Bringing coherent data into the GPU kernel needs some synchronisation between the two elements. We will introduce how to implement that using GPUDirect and present performances obtained with our prototype. Come and see how not to step in the traps we fell into and got out from.

  Back
 
Keywords:
Performance Optimization, Real-Time Graphics, Video and Image Processing, GTC Europe 2017 - ID P23045
 
GPU-Acceleration For Office Workers? Yes! Part 2: Win10/Office2016
Rasmus Raun-Nielsen (CONECTO A/S)
In this session, attendees will learn more about the benefits that a GPU adds to VDI-workloads based on Windows 10- and Office 2016. It is a follow-up to my session from last year on Windows 7- and Office 2013-workloads and their gain from GPUs. ...Read More

In this session, attendees will learn more about the benefits that a GPU adds to VDI-workloads based on Windows 10- and Office 2016. It is a follow-up to my session from last year on Windows 7- and Office 2013-workloads and their gain from GPUs.

  Back
 
Keywords:
Performance Optimization, Other, GTC Europe 2017 - ID 23231
Download:
 
HPE's Deep Learning Cookbook
Sorin Cheran (HPE)
Deep learning is today spearheading a revival in the field of artificial intelligence. Covering a diverse range of industries, such as, car manufacturing, e-commerce, social media, computer software and hardware makers (including HPE), renewable ...Read More

Deep learning is today spearheading a revival in the field of artificial intelligence. Covering a diverse range of industries, such as, car manufacturing, e-commerce, social media, computer software and hardware makers (including HPE), renewable energy and search engines. Deep learning is penetrating into many industry verticals and changing the way they all do business. Yet, any business looking to adapt deep learning, faces inevitable questions for which there are no obvious or immediate answers. Will they need different configurations for different problems they face?

  Back
 
Keywords:
Performance Optimization, Tools and Libraries, Other, GTC Europe 2017 - ID 23245
Download:
 
Dynamic Code Generation and Execution for Monte Carlo Simulations
Vaivaswatha NAGARAJ (NUMERIX LLC), Steve KARMESIN (NUMERIX LLC)
In the work we present here, we dynamically generate code to perform Monte Carlo simulation in the context of a large existing code base for computing prices of financial derivatives where the computation is specified at run time by the user. We ...Read More

In the work we present here, we dynamically generate code to perform Monte Carlo simulation in the context of a large existing code base for computing prices of financial derivatives where the computation is specified at run time by the user. We JIT compile the generated code and execute it on a GPU. We observed speedups of up to about 2x with our method.  

  Back
 
Keywords:
Performance Optimization, Finance, GTC Europe 2017 - ID 23282
Download:
Real-Time Graphics
Presentation
Media
Building Autodesk's VR Centre of Excellence with NVIDIA Quadro
Danny Tierney (AUTODESK GMBH), Simon NAGEL (AUTODESK GMBH)
In the past two years, VR has been made more accessible to the masses with the affordability of HMDs, the availability of high-powered graphic cards, and the development of amazing realtime renderers. Originally, the use cases were seen almost exclus ...Read More
In the past two years, VR has been made more accessible to the masses with the affordability of HMDs, the availability of high-powered graphic cards, and the development of amazing realtime renderers. Originally, the use cases were seen almost exclusively as gaming-oriented, and focused on mass markets with heavily tuned gaming engines. At Autodesk, we have seen the trend turn towards the implementation of these applications within the Automotive, Architecture, Manufacturing and Construction areas. Our presentation will show an array of VR, AR and MR use cases which can be seen live at our Virtual Reality Centre of Excellence in Munich Germany.  Back
 
Keywords:
Real-Time Graphics, Rendering and Ray Tracing, GTC Europe 2017 - ID 23030
 
Optix, a real time sensor (LIDAR) simulation powered by GPUs
Jakub Kolesik (VIRES SIMULATIONSTECHNOLOGIE GMBH)
Virtual testing is the key to the development of ADAS and HAD systems. Research projects on national (PEGASUS) and European (Enable-S3) level have been setup explicitly to define methods and quality criteria for the testing of HAD functions and ...Read More

Virtual testing is the key to the development of ADAS and HAD systems. Research projects on national (PEGASUS) and European (Enable-S3) level have been setup explicitly to define methods and quality criteria for the testing of HAD functions and identify the virtual domain as one of their top priorities. As vehicles depend increasingly on sensors like LIDAR, RADAR and SONAR, an accurate representation of these sensors for test and validation purposes is mandatory. Sensor data will flow into deep learning neural networks on Nvidia Driveworks, or it will be used in software-in-the-loop (SiL) or hardware-in-the-loop (HiL) using Nvidia PX2 for test setups.

  Back
 
Keywords:
Real-Time Graphics, Rendering and Ray Tracing, GTC Europe 2017 - ID 23308
Download:
 
Beyond The Hype:? The Real Value of Enterprise VR
Dan Harper (CITYSCAPE DIGITAL)
Dan Harper of CityscapeVR will explore the huge potential of VR technologies to completely revolutionise business processes in the AEC (Architecture, Engineering, Construction) sector rather than just making small incremental gains. The talk wil ...Read More

Dan Harper of CityscapeVR will explore the huge potential of VR technologies to completely revolutionise business processes in the AEC (Architecture, Engineering, Construction) sector rather than just making small incremental gains. The talk will also explore some case studies showing strong client adoption. VR is here and it is creating a substantial buzz, as well as a lot of questions. Are others using it? ?Is it something I should be using and if so, how? Perhaps most importantly: Why should I be using it? There are many challenges: Technology is moving fast, there are lots of choices of hardware, software etc. Strong opinions are rife across the age brackets. The real question is: How can Virtual Reality and Real-time technologies generate real value within a design business?

  Back
 
Keywords:
Real-Time Graphics, Other, GTC Europe 2017 - ID 23115
Download:
Rendering and Ray Tracing
Presentation
Media
The Virtual Frontier: Computer Graphics Challenges in Virtual & Augmented Reality
Morgan McGuire (NVIDIA)
Game graphics are maturing: near-cinema quality, on sophisticated APIs, game engines, and GPUs. Consumer virtual reality is the Wild West: exciting new opportunities and wide open research challenges. In this talk, Dr. McGuire will identify the ...Read More

Game graphics are maturing: near-cinema quality, on sophisticated APIs, game engines, and GPUs. Consumer virtual reality is the Wild West: exciting new opportunities and wide open research challenges. In this talk, Dr. McGuire will identify the most critical of these challenges and describe how NVIDIA Research is tackling them. The talk will focus on reducing latency, increasing frame rate and field of view, and matching rendering to both display optics and the human visual system.

  Back
 
Keywords:
Rendering and Ray Tracing, GTC Europe 2017 - ID 23262
Download:
 
GTs on GTXs
André Matos (CHAOS GROUP)
Cast a glance at the future with his R&D and expectations into the emerging GPU technologies, the application of new line of photo-realistic scanned materials, made possible by V-Ray RTs fluent work with Nvidias graphic cards. ...Read More

Cast a glance at the future with his R&D and expectations into the emerging GPU technologies, the application of new line of photo-realistic scanned materials, made possible by V-Ray RTs fluent work with Nvidias graphic cards.

  Back
 
Keywords:
Rendering and Ray Tracing, HPC and Supercomputing, Video and Image Processing, GTC Europe 2017 - ID 23435
Download:
Science and Research
Presentation
Media
Deep Reinforcement Learning
Kashif Rasul (ZALANDO SE)
In this hands-on tutorial we will do a deep dive into Deep Reinforcement Learning (DRL), a paradigm which has recently seen a lot of successes. We will introduce you to a variety of DRL algorithms, including Q-learning and Policy Gradient methods. H ...Read More
In this hands-on tutorial we will do a deep dive into Deep Reinforcement Learning (DRL), a paradigm which has recently seen a lot of successes. We will introduce you to a variety of DRL algorithms, including Q-learning and Policy Gradient methods. Hopefully by the end, participants can take this knowledge and apply it to more complex and diverse problems.  Back
 
Keywords:
Science and Research, GTC Europe 2017 - ID 23404
 
Best GPU Code Practices Combining OpenACC, CUDA, and OmpSs
Pau Farre (BARCELONA SUPERCOMPUTING CENTER (BSC)), Antonio PEÑA (BARCELONA SUPERCOMPUTING CENTER (BSC))
We'll guide you step by step to port and optimize an oil-and-gas miniapplication to efficiently leverage the amazing computing power of NVIDIA GPUs. While OpenACC focuses on coding productivity and portability, CUDA enables extracting the maximum pe ...Read More
We'll guide you step by step to port and optimize an oil-and-gas miniapplication to efficiently leverage the amazing computing power of NVIDIA GPUs. While OpenACC focuses on coding productivity and portability, CUDA enables extracting the maximum performance from NVIDIA GPUs. OmpSs, on the other hand, is a GPU-aware task-based programming model that may be combined with CUDA, and recently with OpenACC as well. Using OpenACC, we'll start benefiting from GPU computing, obtaining great coding productivity, and a nice performance improvement. We can next fine-tune the critical application parts developing CUDA kernels to hand-optimize the problem. OmpSs combined with either OpenACC or CUDA will enable seamless task parallelism leveraging all system devices.  Back
 
Keywords:
Science and Research, GTC Europe 2017 - ID 53020
Download:
 
Deployment of Semantic Segmentation Network Using TensorRT
Joohoon Lee (NVIDIA), Chethan NINGARAJU (NVIDIA)
NVIDIA TensorRT is a high-performance neural network inference engine for production deployment of deep learning applications. This lab provides hands-on experience using TensorRT to convert the neural network model to INT8 precision, calibrate, vali ...Read More
NVIDIA TensorRT is a high-performance neural network inference engine for production deployment of deep learning applications. This lab provides hands-on experience using TensorRT to convert the neural network model to INT8 precision, calibrate, vali date and deploy for inference in a self-driving car application.  Back
 
Keywords:
Science and Research, GTC Europe 2017 - ID 53021
Download:
 
Introduction and Integration with DriveWorks on Drive PX2
Aaraadhya Narra (NVIDIA), Alessandro FERRARI (NVIDIA)
NVIDIA® DriveWorks is a Software Development Kit (SDK) that contains reference applications, tools and library modules. It also includes a run-time pipeline framework that goes from detection to localisation and from planning to visualisation. It ...Read More
NVIDIA® DriveWorks is a Software Development Kit (SDK) that contains reference applications, tools and library modules. It also includes a run-time pipeline framework that goes from detection to localisation and from planning to visualisation. It is designed to be educational and open so you can enhance it with your own code. This lab session introduces DriveWorks by running the demos which showcase the available modules. You will learn how to integrate sensors using the Sensor Abstraction Layer provided by DriveWorks, followed by the integration of DriveWorks modules into your custom code or applications. Prerequisites: Basic Linux, C/C++ programming and Deep Learning knowledge  Back
 
Keywords:
Science and Research, GTC Europe 2017 - ID 53022
Download:
 
EGLStreams: Interoperability for Camera, CUDA and OpenGL
Debalina BHATTACHARJEE (NVIDIA), Anshuman BHAT (NVIDIA), Sharan ASHWATHNARAYAN (NVIDIA)
These will be the key takeaway from the lab: 1) Participants will get an overview of EGLStreams implementation 2) We will talk about a wrapper over eglstreams which is easy to plug and play 3) We will describe how to create an eglstream camera produc ...Read More
These will be the key takeaway from the lab: 1) Participants will get an overview of EGLStreams implementation 2) We will talk about a wrapper over eglstreams which is easy to plug and play 3) We will describe how to create an eglstream camera producer and how to connect it to an eglstream CUDA consumer. The consumer will do CUDA processing on a frame received from the camera. 4) We will describe the means of connecting an eglstream camera producer to an eglstream OpenGL consumer. 5) We will describe a means to have multiple eglstreams at the camera producer and different ways to connect these to CUDA and OpenGL consumers. 6) We will also talk about cross process eglstreams. Prerequisites: None  Back
 
Keywords:
Science and Research, GTC Europe 2017 - ID 53023
Download:
 
Step by step implementation and optimization of simulations in quantitative finance
Lokman ABBAS-TURKI (UPMC)
The goal of this lab is to give a guided tour through the essentials of CUDA parallelization in mathematical finance. We consider pricing a bullet option under LV (Local Volatility) model using either MC (Monte Carlo) or an implicit discretization sc ...Read More
The goal of this lab is to give a guided tour through the essentials of CUDA parallelization in mathematical finance. We consider pricing a bullet option under LV (Local Volatility) model using either MC (Monte Carlo) or an implicit discretization scheme for PDE (Partial Differential Equation). The considered example is close to a real banking application with an LV model derived from the implicit SVI model of Gatheral & Jacquier using the Andersen & Brotherton-Ratcliffe expression based on Dupire equation. Several optimizations are studied like the judicious memory storage in shared and registers for two discretization scales in MC. Thanks to a simple trick proposed in Abbas-Turki & Graillat, we see also the use of PCR (Parallel Cyclic Reduction) to solve tridiagonal systems of any size.  Back
 
Keywords:
Science and Research, GTC Europe 2017 - ID 53028
Download:
 
CUDA programming on Drive PX2
Chethan NINGARAJU (NVIDIA)
The main agenda of the workshop is to make you familiar with CUDA programming on Drive PX2 to exploit computational capabilities of the GPUs on Drive PX2. This lab includes: 1) Demonstration of effective usage of unified memory, zero copy, global m ...Read More
The main agenda of the workshop is to make you familiar with CUDA programming on Drive PX2 to exploit computational capabilities of the GPUs on Drive PX2. This lab includes: 1) Demonstration of effective usage of unified memory, zero copy, global memory in an application. 2) We will also demonstrate the performance of dp4A, dp2A intrinsic which are supported on discrete GPU in Drive PX2. 3) Optimization using CUDA streams to overlap memory transfer and kernel execution.  Back
 
Keywords:
Science and Research, GTC Europe 2017 - ID 53032
 
Writing Elegant Host-side code with Modern-C++ CUDA Runtime API wrappers
Eyal Rozenberg (CWI AMSTERDAM)
In this lab we'll experience writing host-side code for CUDA programs in modern C++, elegantly. Taking a sample program with a simple kernel, we'll make its code safer in handling errors and allocations; clearer to read; and shorter - without im ...Read More
In this lab we'll experience writing host-side code for CUDA programs in modern C++, elegantly. Taking a sample program with a simple kernel, we'll make its code safer in handling errors and allocations; clearer to read; and shorter - without imposing any restrictions on the use of API features, and without loss of performance. We'll achieve this by gradually converting aspects of the C-style API to using a FOSS header-mostly wrapper library (https://github.com/eyalroz/cuda-api-wrappers), and more C++ idiomatic constructs. The following kinds of code will definitely be covered: (*) host- and device-side memory allocation (*) Copying data (*) Enqueuing launches and events on streams (*) Streamlined error handling as will additional API aspects or implementation details as time allows.  Back
 
Keywords:
Science and Research, GTC Europe 2017 - ID 53033
Download:
 
Image Classification & Object Detection using Deep Learning & MATLAB
Girish Venkataramani (MATHWORKS), Alexander Schreiber (MATHWORKS), Bill CHOU (MATHWORKS)
This lab will use an object recognitionundefinedimage classification example to teach how to apply deep learning to practical problems. You will learn how to: import and manage large datasets; train, evaluate and compare different deep learning model ...Read More
This lab will use an object recognitionundefinedimage classification example to teach how to apply deep learning to practical problems. You will learn how to: import and manage large datasets; train, evaluate and compare different deep learning models; extract discriminative information from images, and; use transfer learning to fine-tune neural networks for new tasks. We will use the new MATLAB framework for deep learning and real-world examples including data used for ADAS and autonomous driving.  Back
 
Keywords:
Science and Research, GTC Europe 2017 - ID 53035
 
Jetson TX2 Developer Tools
Felix SCHMITT (NVIDIA), Thomas KLEIN (NVIDIA)
This lab is focused on teaching you how to maximize the productivity when developing software for the Jetson platform. You will experience first hand how to manage source code on the host PC to cross-compile the software, initiate remote debugging se ...Read More
This lab is focused on teaching you how to maximize the productivity when developing software for the Jetson platform. You will experience first hand how to manage source code on the host PC to cross-compile the software, initiate remote debugging sessions to debug CPU CundefinedC++ and CUDA C code. Through a comprehensive set of exercises, you will also learn how to use the CUDA Visual Profiler for optimizing CUDA kernels, use the Tegra System Profiler for optimizing CPU code and tracing multi-process system-wide activities, and use Tegra Graphics Debugger for debugging and profiling 3D graphics applications.  Back
 
Keywords:
Science and Research, GTC Europe 2017 - ID 53036
Download:
 
Distributed Deep Learning using Apache MXNet on AWS
Vikram MADAN (AMAZON WEB SERVICES), Cyrus VAHID (AMAZON WEB SERVICES)
In this lab, we will cover deep learning fundamentals and focus on the powerful and scalable Apache MXNet open source deep learning framework. At the end of this hands on lab, youll be able to train your own deep neural network and fine tune exi ...Read More

In this lab, we will cover deep learning fundamentals and focus on the powerful and scalable Apache MXNet open source deep learning framework. At the end of this hands on lab, youll be able to train your own deep neural network and fine tune existing state of the art models for image and object recognition. Well also dive deep into setting up your deep learning infrastructure on AWS.

  Back
 
Keywords:
Science and Research, GTC Europe 2017 - ID 53491
Self-Driving Cars
Presentation
Media
Why the Self-Driving Revolution Hinges on one Enabling Technology: LiDAR
Markus Prison (QUANERGY SYSTEMS)
As the race to create self-driving vehicles heats up, there’s one question that is asked time and again: when will self-driving cars become mainstream? One thing is for sure: it depends on the development of one key piece of technology, Li ...Read More

As the race to create self-driving vehicles heats up, there’s one question that is asked time and again: when will self-driving cars become mainstream? One thing is for sure: it depends on the development of one key piece of technology, LiDAR. For self-driving cars to safely navigate their environments, they must be able to detect and recognize people, other vehicles, roadways, road markings, traffic signs, bridges, and other objects, and place them accurately to synthesize a 3D view. The evolution of LiDAR smart sensing technology into solid state solutions is embodied by sensors that contain no moving parts. This presentation will discuss integrated solid state LiDAR sensor solutions, and will cover commercial advancements that made sophisticated 3D mapping and object detection.

  Back
 
Keywords:
Self-Driving Cars, Other, GTC Europe 2017 - ID 23328
Download:
 
Deep Learning for Autonomous Driving: From advanced perception to end-to-end driving
Xavier PERROTTON (VALEO), Maximilian JARITZ (VALEO)
1 - Valeo automated Driving Roadmap 2 - Deep learning as a key lever for Automated Driving 3 - Advanced Perception by Deep Neural Network => 3D object detection for surround cameras in partnership with CEA DeepManta - Current results on PC wi ...Read More

1 - Valeo automated Driving Roadmap 2 - Deep learning as a key lever for Automated Driving 3 - Advanced Perception by Deep Neural Network => 3D object detection for surround cameras in partnership with CEA DeepManta - Current results on PC with NVIDIA graphic board - Potential embedded results on NVIDIA DrivePx2 (TBC) 4 - End to End driving by Reinforcement Learning on a racing game 5 - Conclusion

  Back
 
Keywords:
Self-Driving Cars, GTC Europe 2017 - ID 23108
Download:
 
Software Development for Active Safety and Autonomous Driving Technology
Erik Coelingh (ZENUITY)
This session will descibe how Zenuity addresses the key challenges when developing software for self-driving vehicles. Zenuity originates from the safety leaders of the automotive industry and is developing a complete software stack from sensors ...Read More

This session will descibe how Zenuity addresses the key challenges when developing software for self-driving vehicles. Zenuity originates from the safety leaders of the automotive industry and is developing a complete software stack from sensors to actuators. Advanced computer vision in combination with radar technology and capable computational platforms have created a revolution in this field and accident statistics show that it has a significant positive impact on traffic safety.

  Back
 
Keywords:
Self-Driving Cars, GTC Europe 2017 - ID 23118
Download:
 
A Centralized Functional Approach to Developing Self-Driving Trucks
Ralf WELLER (MAN TRUCK & BUS AG)
This presentation will bring you a insight into the truck business by focusing on the technology of autonomous driving. A short look at the business opportunities and derived use cases will unveil challenges and difficulties. Presenting the status q ...Read More
This presentation will bring you a insight into the truck business by focusing on the technology of autonomous driving. A short look at the business opportunities and derived use cases will unveil challenges and difficulties. Presenting the status quo of the in-house development method at the MAN Truck & Bus AG, it will be shown in detail how the so called functional approach will be a perfect basis for the future of autonomous driving. It ensures reusability of software and hardware independency. By looking at the electrical and electronic architecture of the future the main requirements for two centralized control units is reasoned in detail, together with the requirements of processors and GPUs.  Back
 
Keywords:
Self-Driving Cars, GTC Europe 2017 - ID 23276
Download:
 
Deep learning for self-driving cars in simulation and going real
Jost Bernasch (VIRTUAL VEHICLE RESEARCH CENTER)
Deep learning is one of the key cornerstones for self-driving cars. Still, we face the problem of collecting a crucial amount of data and labelling it for training. The accuracy of deep neural nets heavily depends on the chosen architecture but ...Read More

Deep learning is one of the key cornerstones for self-driving cars. Still, we face the problem of collecting a crucial amount of data and labelling it for training. The accuracy of deep neural nets heavily depends on the chosen architecture but also on the available training data. Approaches like transfer learning or collecting training data in virtual environments are common solutions. However, both solutions require a lot of fine tuning afterwards. We investigate in deep learning approaches, which are pre-trained in simple simulation conditions. This, helps us to reduce the effort of collecting the amount of real data, but does not rely on a very complex and expensive simulation. Later the network is further fine-tuned and tested on our real demonstration car.

  Back
 
Keywords:
Self-Driving Cars, GTC Europe 2017 - ID 23284
Download:
 
Automating last mile delivery
Fabian SCHMITT (DEUTSCHE POST)
Automation of last mile delivery is a key topic to ensure future logistics. Concepts include autonomous driving, drones and intelligent parcel stations, using NVIDIA DPX Platform. ...Read More

Automation of last mile delivery is a key topic to ensure future logistics. Concepts include autonomous driving, drones and intelligent parcel stations, using NVIDIA DPX Platform.

  Back
 
Keywords:
Self-Driving Cars, GTC Europe 2017 - ID 23333
Download:
 
Highly Iterative Approach Towards Autonomous Driving
Günther Schuh (E.GO MOBILE AG)
Todays manufacturers are challenged by constantly growing customer expectations while facing a changing market environment. One way to handle those requirements is the highly iterative product development approach. By spreading the development i ...Read More

Todays manufacturers are challenged by constantly growing customer expectations while facing a changing market environment. One way to handle those requirements is the highly iterative product development approach. By spreading the development in short and iterative sub-processes this method generates customer oriented products. Since its founding, the German automotive company e.GO Mobile AG follows agile development structures also in the research field of autonomous driving for electric vehicles. By designing platform-based concepts in a flexible development environment, the company successfully generates innovative products and also creates new markets. In May this year, e.GO presented the third product of the e.GO-family, the e.GO Mover, an electric, autonomous driving people mover.

  Back
 
Keywords:
Self-Driving Cars, GTC Europe 2017 - ID 23380
Download:
 
How Microcontrollers help GPUs in Autonomous Drive
Hans ADLKOFER (INFINEON TECHNOLOGIES)
Attendees can learn fundamentals of Automotive Safety and Sensor fusion ECU architectures, as well as challenges ahead for Microcontrollers. Introduction of some Safety concepts (Dependability, Hardware safety platform), as well as architectures ...Read More

Attendees can learn fundamentals of Automotive Safety and Sensor fusion ECU architectures, as well as challenges ahead for Microcontrollers. Introduction of some Safety concepts (Dependability, Hardware safety platform), as well as architectures and partitioning of functionalities in a Sensor Fusion ECU, between microcontroller, GPU and CPU will be developed. Key problematics and challenges of the Automotive manufacturers to ensure Safety (such as fail operational architectures, cybersecurity, reliability, latencies ) and the role of microcontrollers will be discussed.

  Back
 
Keywords:
Self-Driving Cars, GTC Europe 2017 - ID 23382
Download:
 
On the Road to Vision Zero - how Vehicles will be able to see, think and act
Stefan SOMMER (ZF FRIEDRICHSHAFEN AG)
Zero emissions and zero accidents. ZFs goal of Vision Zero for world roadways is based on a broad scope of advanced safety and highly efficient driveline technologies along with its ecosystem of strong industry partners. One enabler is the sound ...Read More

Zero emissions and zero accidents. ZFs goal of Vision Zero for world roadways is based on a broad scope of advanced safety and highly efficient driveline technologies along with its ecosystem of strong industry partners. One enabler is the sound base of intelligent mechanical systems which interact and communicate through a powerful networked main processor. Based upon NVIDIA core technology, ZF ProAI is the right data processing platform to help realize autonomous driving in a safe environment. Powerful, scalable and reliable, it is able to command the interaction between the sensors and the actuators and is helping introduce Artificial Intelligence into the mobility world. The technology not only applies to passenger cars but also to commercial vehicles, industrial applications and new

  Back
 
Keywords:
Self-Driving Cars, GTC Europe 2017 - ID 23489
Download: