GTC ON-DEMAND

 
SEARCH SESSIONS
SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Presentation
Media
Abstract:

We'll present a deep learning-based analysis framework for making key decisions about heart valve replacement and valve design. We'll describe how we use deep learning to predict valve performance measures, which makes these measurements accessible to physicians who lack expert computational knowledge. We will explain how our trained DL framework can be used interactively to predict valve-performance measures with the same fidelity as time-consuming biomechanics simulations. We'll also discuss how our tool can help doctors with heart valve diagnosis, ultimately improving patient care.

We'll present a deep learning-based analysis framework for making key decisions about heart valve replacement and valve design. We'll describe how we use deep learning to predict valve performance measures, which makes these measurements accessible to physicians who lack expert computational knowledge. We will explain how our trained DL framework can be used interactively to predict valve-performance measures with the same fidelity as time-consuming biomechanics simulations. We'll also discuss how our tool can help doctors with heart valve diagnosis, ultimately improving patient care.

  Back
 
Topics:
Medical Imaging & Radiology, AI & Deep Learning Research, Consumer Engagement & Personalization
Type:
Talk
Event:
GTC Silicon Valley
Year:
2019
Session ID:
S9455
Streaming:
Download:
Share:
 
Abstract:
Voxelized representation of 3D objects is commonly used for training 3D-Convolutional Neural Networks for object detection and classification. However, high-resolution voxelization of CAD models are memory intensive and hence, it is not possible to load multiple models in the GPU for training. We have developed a GPU-accelerated voxelization technique that generates multi-level voxel grids of 3D objects. Instead of creating a single high-resolution voxel grid for the whole object, this technique generates selective region-based high-resolution voxel grids to represent detailed features in the object. We have also developed a multi-resolution 3D-Convolutional Neural Network that uses this hybrid voxelization for accurate object recognition and classification.
Voxelized representation of 3D objects is commonly used for training 3D-Convolutional Neural Networks for object detection and classification. However, high-resolution voxelization of CAD models are memory intensive and hence, it is not possible to load multiple models in the GPU for training. We have developed a GPU-accelerated voxelization technique that generates multi-level voxel grids of 3D objects. Instead of creating a single high-resolution voxel grid for the whole object, this technique generates selective region-based high-resolution voxel grids to represent detailed features in the object. We have also developed a multi-resolution 3D-Convolutional Neural Network that uses this hybrid voxelization for accurate object recognition and classification.  Back
 
Topics:
AI & Deep Learning Research, Industrial Inspection, Computer Vision
Type:
Talk
Event:
GTC Silicon Valley
Year:
2018
Session ID:
S8389
Streaming:
Download:
Share:
 
Abstract:
We'll present a GPU-accelerated deep-learning framework for cyber-manufacturing, which enables real-time feedback to designers regarding the manufacturability of a computer-aided design model. We'll talk about a 3D-convolutional neural network-based approach for learning the manufacturability of a mechanical component. The 3D-CNN can recognize the features in a CAD model and classify it to be manufacturable or non-manufacturable with a greater accuracy than traditional rule-based methods. We'll discuss a novel GPU-accelerated voxelization algorithm used to discretize the CAD model and prepare it for deep learning. We'll briefly outline the challenges in training a 3D-CNN using complex CAD models on a GPU (NVIDIA TITAN X) with limited memory. Finally, we'll touch upon different methods to extend the framework to other manufacturing processes, such as additive manufacturing and milling.
We'll present a GPU-accelerated deep-learning framework for cyber-manufacturing, which enables real-time feedback to designers regarding the manufacturability of a computer-aided design model. We'll talk about a 3D-convolutional neural network-based approach for learning the manufacturability of a mechanical component. The 3D-CNN can recognize the features in a CAD model and classify it to be manufacturable or non-manufacturable with a greater accuracy than traditional rule-based methods. We'll discuss a novel GPU-accelerated voxelization algorithm used to discretize the CAD model and prepare it for deep learning. We'll briefly outline the challenges in training a 3D-CNN using complex CAD models on a GPU (NVIDIA TITAN X) with limited memory. Finally, we'll touch upon different methods to extend the framework to other manufacturing processes, such as additive manufacturing and milling.  Back
 
Topics:
Intelligent Machines, IoT & Robotics, Artificial Intelligence and Deep Learning, Computational Fluid Dynamics, Computer Aided Engineering, AEC & Manufacturing
Type:
Talk
Event:
GTC Silicon Valley
Year:
2017
Session ID:
S7397
Download:
Share:
 
Abstract:
The aim of this project is to create designer, 3D, shaped polymer particles for engineering applications by combining masked photo-polymerization and flow sculpting in orthogonal directions. The final particle shape is the intersection of these 2D orthogonal cross-sections. We use GPUs to generate voxelized representation of the particle shape. We then use constrained optimization with GPU acceleration to solve the inverse problem of generating the required cross-sections that will create the desired 3D particle shape
The aim of this project is to create designer, 3D, shaped polymer particles for engineering applications by combining masked photo-polymerization and flow sculpting in orthogonal directions. The final particle shape is the intersection of these 2D orthogonal cross-sections. We use GPUs to generate voxelized representation of the particle shape. We then use constrained optimization with GPU acceleration to solve the inverse problem of generating the required cross-sections that will create the desired 3D particle shape  Back
 
Topics:
AEC & Manufacturing, Computational Physics
Type:
Poster
Event:
GTC Silicon Valley
Year:
2015
Session ID:
P5197
Download:
Share:
 
Abstract:

We present new GPU algorithms for computing the directed Hausdorff distance between freeform surfaces, with applications in shape matching, mesh simplification, and geometric approximation and optimization. Our algorithms run in real-time with very small error bounds for parametric models defined by complex NURBS surfaces and can be used to interactively compute the Hausdorff distance for models made of dynamic deformable surfaces. We discuss implementation decisions and tradeoffs between OpenGL, Cuda, and Thrust, and the advantages and disadvantages of parallel hierarchical culling methods for this application.

We present new GPU algorithms for computing the directed Hausdorff distance between freeform surfaces, with applications in shape matching, mesh simplification, and geometric approximation and optimization. Our algorithms run in real-time with very small error bounds for parametric models defined by complex NURBS surfaces and can be used to interactively compute the Hausdorff distance for models made of dynamic deformable surfaces. We discuss implementation decisions and tradeoffs between OpenGL, Cuda, and Thrust, and the advantages and disadvantages of parallel hierarchical culling methods for this application.

  Back
 
Topics:
Developer - Algorithms
Type:
Talk
Event:
GTC Silicon Valley
Year:
2012
Session ID:
S2410
Streaming:
Download:
Share:
 
Speakers:
Adarsh Krishnamurthy, Sara McMains
- University of California Berkeley
Abstract:
The broad objective of our research is to develop mechanical Computer-Aided Design tools that provide interactive feedback to the designer. We have developed GPU algorithms for fundamental CAD operations (NURBS evaluation, surface-surface intersection, separation distance computation, moment computation, etc.) that are one to two orders of magnitude faster, and often more accurate, than current commercial CPU implementations. We will touch on strategies we have employed to meet GPU programming challenges, such as the separation of CPU/GPU operations, imposing artificial structure on computations, and transforming problem definitions to suit GPU-computation models.
The broad objective of our research is to develop mechanical Computer-Aided Design tools that provide interactive feedback to the designer. We have developed GPU algorithms for fundamental CAD operations (NURBS evaluation, surface-surface intersection, separation distance computation, moment computation, etc.) that are one to two orders of magnitude faster, and often more accurate, than current commercial CPU implementations. We will touch on strategies we have employed to meet GPU programming challenges, such as the separation of CPU/GPU operations, imposing artificial structure on computations, and transforming problem definitions to suit GPU-computation models.  Back
 
Topics:
Developer - Algorithms, Tools & Libraries, Graphics and AI
Type:
Talk
Event:
GTC Silicon Valley
Year:
2010
Session ID:
S102171
Streaming:
Download:
Share:
 
Speakers:
Adarsh Krishnamurthy
- University of California, Berkeley
Abstract:
We present GPU algorithms and strategies for accelerating distance queries and clearance computations on models made of trimmed NURBS surfaces. We provide a generalized framework for using GPUs as co-processors in accelerating CAD operations. The accuracy of our algorithm is based on the model space precision, unlike earlier graphics algorithms that were based only on image space precision. Our algorithms are at least an order of magnitude faster and about two orders of magnitude more accurate than the commercial solid modeling kernel ACIS.
We present GPU algorithms and strategies for accelerating distance queries and clearance computations on models made of trimmed NURBS surfaces. We provide a generalized framework for using GPUs as co-processors in accelerating CAD operations. The accuracy of our algorithm is based on the model space precision, unlike earlier graphics algorithms that were based only on image space precision. Our algorithms are at least an order of magnitude faster and about two orders of magnitude more accurate than the commercial solid modeling kernel ACIS.  Back
 
Topics:
Developer - Algorithms
Type:
Poster
Event:
GTC Silicon Valley
Year:
2010
Session ID:
P10A15
Download:
Share:
 
 
Previous
  • Amazon Web Services
  • IBM
  • Cisco
  • Dell EMC
  • Hewlett Packard Enterprise
  • Inspur
  • Lenovo
  • SenseTime
  • Supermicro Computers
  • Synnex
  • Autodesk
  • HP
  • Linear Technology
  • MSI Computer Corp.
  • OPTIS
  • PNY
  • SK Hynix
  • vmware
  • Abaco Systems
  • Acceleware Ltd.
  • ASUSTeK COMPUTER INC
  • Cray Inc.
  • Exxact Corporation
  • Flanders - Belgium
  • Google Cloud
  • HTC VIVE
  • Liqid
  • MapD
  • Penguin Computing
  • SAP
  • Sugon
  • Twitter
Next