Geometric deep learning and equivariant neural networks
We survey the mathematical foundations of geometric deep learning, focusing on group
equivariant and gauge equivariant neural networks. We develop gauge equivariant
convolutional neural networks on arbitrary manifolds M using principal bundles with
structure group K and equivariant maps between sections of associated vector bundles. We
also discuss group equivariant neural networks for homogeneous spaces M= G/K, which are
instead equivariant with respect to the global symmetry G on M. Group equivariant layers …
equivariant and gauge equivariant neural networks. We develop gauge equivariant
convolutional neural networks on arbitrary manifolds M using principal bundles with
structure group K and equivariant maps between sections of associated vector bundles. We
also discuss group equivariant neural networks for homogeneous spaces M= G/K, which are
instead equivariant with respect to the global symmetry G on M. Group equivariant layers …
[CITATION][C] Geometric Deep Learning and Equivariant Neural Networks. arXiv 2021
JE Gerken, J Aronsson, O Carlsson, H Linander… - arXiv preprint arXiv:2105.13926
Showing the best results for this search. See all results