Numerical Analysis Seminar: Risi Kondor

Date & Time


Title: Covariant neural network architectures for learning physics

Abstract: Deep neural networks have proved to be extremely effective in image recognition, machine translation, and a variety of other data centered engineering tasks. However, generalizing neural networks to learning physical systems requires a careful examination of how they reflect symmetries. In this talk we give an overview of recent developments in the field of covariant/equivariant neural networks. Specifically, we focus on three applications: learning properties of chemical compounds from their molecular structure, image recognition on the sphere, and learning force fields for molecular dynamics. The work presented in this talk was done in collaboration with Brandon Anderson, Zhen Lin, Truong Son Hy, Horace Pan, and Shubhendu Trivedi.

Our seminar focuses on efficient computational methods for numerical problems, mostly phrased in a mathematical language, arising in areas of science throughout the Institute and beyond. Topics include signal processing and data analysis (spike sorting of neural recordings, cryo-EM for protein imaging, audio representation); computational statistics (with applications such as the ocean microbiome); PDEs (fluid flow, waves), integral equations, spectral methods, “fast” algorithms (i.e., close to optimal complexity); software libraries and programming. We discuss research topics as well as review classical topics in numerical analysis.

Advancing Research in Basic Science and MathematicsSubscribe to Flatiron Institute announcements and other foundation updates