基于梯度下降学习的过参数化卷积神经网络图像分类器收敛率分析
机器学习
2024-05-14 v1 机器学习
摘要
考虑基于过参数化卷积神经网络进行图像分类，网络中包含全局平均池化层。该网络的权重通过梯度下降法学习。推导了该卷积神经网络估计的误分类风险与最小可能值之间差异收敛速率的上界。
引用
@article{arxiv.2405.07619,
title = {Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent},
author = {Michael Kohler and Adam Krzyzak and Benjamin Walter},
journal= {arXiv preprint arXiv:2405.07619},
year = {2024}
}