Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kohler, Michael, Krzyzak, Adam, Walter, Benjamin
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914793981476864
author Kohler, Michael
Krzyzak, Adam
Walter, Benjamin
author_facet Kohler, Michael
Krzyzak, Adam
Walter, Benjamin
contents Image classification based on over-parametrized convolutional neural networks with a global average-pooling layer is considered. The weights of the network are learned by gradient descent. A bound on the rate of convergence of the difference between the misclassification risk of the newly introduced convolutional neural network estimate and the minimal possible value is derived.
format Preprint
id arxiv_https___arxiv_org_abs_2405_07619
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent
Kohler, Michael
Krzyzak, Adam
Walter, Benjamin
Machine Learning
Image classification based on over-parametrized convolutional neural networks with a global average-pooling layer is considered. The weights of the network are learned by gradient descent. A bound on the rate of convergence of the difference between the misclassification risk of the newly introduced convolutional neural network estimate and the minimal possible value is derived.
title Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent
topic Machine Learning
url https://arxiv.org/abs/2405.07619