Machine Learning at the Flatiron Institute Seminar: Soledad Villar

Date & Time

Title: Exact and approximate symmetries in machine learning

Abstract: In this talk, we explain how we can use invariant theory tools to express machine learning models that preserve symmetries arising from physical law. We consider applications to self-supervised contrastive learning, time series of graphs, and cosmology.

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