On the Interplay Between Deep Learning and Dynamical Systems
Rose Yu
UCSD
Abstract:
The explosion of spatiotemporal data in the physical world requires new deep-learning tools to model complex dynamical systems. On the other hand, dynamical system theory plays a key role in understanding the emerging behavior of deep neural networks. In this talk, I will give an overview of our research to explore the interplay between the two. I will showcase the applications of these approaches in fluid mechanics, autonomous driving, and optimization.
Tuesday, February 13, 2024
11:00AM Zoom Only, ID 990 3560 4352