Approximately Equivariant Networks for Imperfectly Symmetric Dynamics. (arXiv:2201.11969v1 [cs.LG])

Web: http://arxiv.org/abs/2201.11969

Incorporating symmetry as an inductive bias into neural network architecture
has led to improvements in generalization, data efficiency, and physical
consistency in dynamics modeling. Methods such as CNN or equivariant neural
networks use weight tying to enforce symmetries such as shift invariance or
rotational equivariance. However, despite the fact that physical laws obey many
symmetries, real-world dynamical data rarely conforms to strict mathematical
symmetry either due to noisy or incomplete data or to symmetry breaking
features in the underlying dynamical …

arxiv networks