Learning Physical Law Reliably

Gitta Kutyniok

Physical law learning is the ambiguous attempt at automating the derivation of governing equations with the use of machine learning techniques. We approach this problem from a mathematical perspective, taking also aspects such as reliability of the learning algorithm into account. In this talk, we will provide an introduction into this vibrant research area also discussing its importance for simulation sciences. We will then present our theoretical approach alongside with extensive numerical experiments.

To the top of the page