SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Presentation
Media
Abstract:
Learn how to accelerate deep learning-based image recognition applications on the 5G network, the next-generation cellular mobile network. The 5G network will enable low latency and high data-rate telecommunication, making it suitable for deep learning applications that need to post and get large amounts of data via the network or need real-time inference. We'll discuss how we're working to use these 5G characteristics by developing image- and video-recognition services on the mobile phone network. These include surveillance-camera recognition, adaptive digital signage, and image recognition for retail companies. In addition, we'll explain how to make telecommunication between the edge application and the cloud resource more secure and more efficient for deep learning applications.
Learn how to accelerate deep learning-based image recognition applications on the 5G network, the next-generation cellular mobile network. The 5G network will enable low latency and high data-rate telecommunication, making it suitable for deep learning applications that need to post and get large amounts of data via the network or need real-time inference. We'll discuss how we're working to use these 5G characteristics by developing image- and video-recognition services on the mobile phone network. These include surveillance-camera recognition, adaptive digital signage, and image recognition for retail companies. In addition, we'll explain how to make telecommunication between the edge application and the cloud resource more secure and more efficient for deep learning applications.  Back
 
Topics:
5G & Edge, AI & Deep Learning Research, Computer Vision
Type:
Talk
Event:
GTC Silicon Valley
Year:
2019
Session ID:
S9718
Streaming:
Download:
Share:
 
Abstract:
We'll show a brief overview of our deep learning applications such as image recognition and taxi demand forecasts and how we have accelerated our development using NVIDIA Docker, the NVIDIA DGX-1 AI supercomputer, and tens of GPU servers. As deep learning applications become widespread, it becomes more essential for engineers to quickly adapt deep learning to new data and to efficiently seek optimal configurations. To improve the development speed by engineers on the shared GPU resources, we developed a job management system, which provides the separated learning environment for each engineer using NVIDIA Docker and queuing functions on the multi-GPU/multi-node system. This system helps us improve our productivity and create more sophisticated solutions to offer better services.
We'll show a brief overview of our deep learning applications such as image recognition and taxi demand forecasts and how we have accelerated our development using NVIDIA Docker, the NVIDIA DGX-1 AI supercomputer, and tens of GPU servers. As deep learning applications become widespread, it becomes more essential for engineers to quickly adapt deep learning to new data and to efficiently seek optimal configurations. To improve the development speed by engineers on the shared GPU resources, we developed a job management system, which provides the separated learning environment for each engineer using NVIDIA Docker and queuing functions on the multi-GPU/multi-node system. This system helps us improve our productivity and create more sophisticated solutions to offer better services.  Back
 
Topics:
Artificial Intelligence and Deep Learning, Accelerated Data Science
Type:
Talk
Event:
GTC Silicon Valley
Year:
2017
Session ID:
S7554
Download:
Share: