Towards Cross Domain Generalization of Hamiltonian Representation via Meta Learning

arXiv:2212.01168v4 Announce Type: replace
Abstract: Recent advances in deep learning for physics have focused on discovering shared representations of target systems by incorporating physics priors or inductive biases into neural networks. While effective, these methods are limited to the system domain, where the type of system remains consistent and thus cannot ensure the adaptation to new, or unseen physical systems governed by different laws. For instance, a neural network trained on a mass-spring system cannot guarantee accurate predictions for the …

abstract advances arxiv biases consistent cs.ai cs.lg deep learning domain inductive meta networks neural networks physics physics.comp-ph representation systems type via while