ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive Bias

1 code implementation • 24 Jun 2022 • Yupu Lu, ShiJie Lin, Guanqi Chen, Jia Pan

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 different numbers of elements (e. g., double- and triple-pendulum systems).

Inductive Bias

Modular Lagrangian Neural Networks: Designing Structures of Networks with Physical Inductive Biases

no code implementations • 29 Sep 2021 • Yupu Lu, ShiJie Lin, Jia Pan

At the same time, we directly applied our trained models to predict the motion of multi-pendulum and multi-body systems, demonstrating the intriguing performance in the extrapolation of our method.