VC dimensions of group convolutional neural networks.
Neural Netw
; 169: 462-474, 2024 Jan.
Article
em En
| MEDLINE
| ID: mdl-37939535
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.
Palavras-chave
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Algoritmos
/
Redes Neurais de Computação
Idioma:
En
Ano de publicação:
2024
Tipo de documento:
Article