Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent
Abstract
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- May 2024
- DOI:
- 10.48550/arXiv.2405.07619
- arXiv:
- arXiv:2405.07619
- Bibcode:
- 2024arXiv240507619K
- Keywords:
-
- Statistics - Machine Learning;
- Computer Science - Machine Learning