GTC 2020: Interactive Deep Learning: Using the GPU for Visual Insight into Training and Inference

GTC 2020 S21313
Presenters: Don Brittain,NVIDIA
Abstract
The GPU was originally created to drive interactive, highly-visual applications. Because of their massive computation power, GPUs are also excellent for deep-learning training and inference. By capitalizing on both of these strengths during DL development, we can gain insight into model design, loss-function performance, and inference optimization opportunities. We’ll show some ways that interactive visual processing can help streamline DL development, from model design through final deployment. Our session’s geared toward application programmers and other AI practitioners, but it should also be accessible to program designers and project managers interested in incorporating AI features into your products.

Watch this session
Join in the conversation below.