arXiv Open Access 2024

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

Michael Kohler Adam Krzyzak Benjamin Walter

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

stat.ML cs.LG

Penulis (3)

Michael Kohler

Adam Krzyzak

Benjamin Walter

Format Sitasi

APA MLA BibTeX

Kohler, M., Krzyzak, A., Walter, B. (2024). Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent. https://arxiv.org/abs/2405.07619

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2024
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓