Geometric deep learning and equivariant neural networks

JE Gerken, J Aronsson, O Carlsson, H Linander… - Artificial Intelligence …, 2023 - Springer
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 …

[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