Incorporating Symmetry for Improved Deep Dynamics Learning

Applied and Computational Mathematics Seminar
Monday, September 13, 2021 - 2:00pm for 1 hour (actually 50 minutes)
Prof. Rose Yu – UCSD
Molei Tao

While deep learning has been used for dynamics learning, limited physical accuracy and an inability to generalize under distributional shift limit its applicability to real world. In this talk, I will demonstrate how to incorporate symmetries into deep neural networks and significantly improve the physical consistency, sample efficiency, and generalization in learning dynamics. I will showcase the applications of these models to challenging problems such as turbulence forecasting and trajectory prediction for autonomous vehicles.