Title: Learning about symmetries and integrability of physical systems with AI

Speaker: Sven Krippendorf (LMU Munich)

Time: 16:15-16:50 (GMT+0), 2021.08.05

Abstract:

AI can be used for finding structures in data from scratch, i.e. without knowing about them beforehand. One might wonder whether AI can be used to find the symmetries of a system or to decide whether a dynamical system is integrable or not? In this talk, I report on how we can set up machines to successfully search for symmetries and the Lax pair/connection in some classical examples. We shall also see how symbolic regression can be used to render the output interpretable for a physicist. This talk is based on 2103.07475, 2104.14444, and 2003.13679.