Titel
VC dimensions of group convolutional neural networks
Abstract
We study the generalization capacity of group convolutional neural networks. We identify precise estimates for the VC dimensions of simple sets of group convolutional neural networks. In particular, we find that for infinite groups and appropriately chosen convolutional kernels, already two-parameter families of convolutional neural networks have an infinite VC dimension, despite being invariant to the action of an infinite group.
Stichwort
Convolutional neural networksGroup convolutional neural networksSample complexityGeneralizationVC dimension
Objekt-Typ
Sprache
Englisch [eng]
Persistent identifier
phaidra.univie.ac.at/o:2044746
Erschienen in
Titel
Neural Networks
Band
169
ISSN
0893-6080
Erscheinungsdatum
2024
Seitenanfang
462
Seitenende
474
Publication
Elsevier BV
Erscheinungsdatum
2024
Zugänglichkeit
Rechte
Rechteangabe
© 2023 The Authors
Universität Wien | Universitätsring 1 | 1010 Wien | T
+43-1-4277-0