Bryan Catanzaro: Applications of Deep Learning in Graphics, Conversational AI, and Systems Design

EECS Colloquium Wednesday, April 7, 2021 4:00​​ - 5:00 pm Bryan Catanzaro Vice President of Applied Deep Learning Research NVIDIA Abstract: Applications of deep learning are numerous and exciting, but actually applying deep learning to solve particular problems is rarely straightforward. Bryan will discuss research to solve concrete graphics, conversational AI, and systems design problems at NVIDIA. Applying deep learning requires inventing algorithms, creating datasets, scaling on large systems, and framing real-world problems as machine learning. In this talk, Bryan will give examples of each of these: the Flowtron and Waveglow speech synthesis models that pioneered invertible flow models for lifelike human speech synthesis; DLSS - the first neural reconstruction method for graphics rendering that provides increased framerate for video games; the neural networks that power intelligent code selection to speed up GPU-based deep learning computation; and the Megatron framework that enables training the large