FI Computational Methods and Data Science Journal Club: Robin Walters

Thursday Nov 11, 2021, 3:00 PM → 5:00 PM America/New_York

CCA, 5th Floor Classroom (Flatiron Institute)

 

FI Computational Methods and Data Science Journal Club

Flatiron Institute, 162 5th Avenue

Speaker: Robin Walters

Title: Equivariant Neural Networks for Learning Spatiotemporal Dynamics

Abstract: Applications such as climate science and transportation require learning complex dynamics from large-scale spatiotemporal data. Existing machine learning frameworks are still insufficient to learn spatiotemporal dynamics as they often fail to exploit the underlying physics principles. Representation theory can be used to describe and exploit the symmetry of the dynamical system. We will show how to design neural networks that are equivariant to various symmetries for learning spatiotemporal dynamics. Our methods demonstrate significant improvement in prediction accuracy, generalization, and sample efficiency in forecasting turbulent flows and predicting real-world trajectories. This is joint work with Rose Yu, Rui Wang, and Jinxi Li.

FI employees are welcome. Visitors please email ccaadmin@flatironinstitute.org to register.