ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive BiasDownload PDFOpen Website

Published: 01 Jan 2022, Last Modified: 12 May 2023ICML 2022Readers: Everyone
Abstract: Deep learning models are able to approximate one specific dynamical system but struggle at learning generalisable dynamics, where dynamical systems obey the same laws of physics but contain differe...
0 Replies

Loading