On the rate of convergence of image classifiers based on convolutional neural networks
Machine Learning
2020-10-16 v3 Machine Learning
Abstract
Image classifiers based on convolutional neural networks are defined, and the rate of convergence of the misclassification risk of the estimates towards the optimal misclassification risk is analyzed. Under suitable assumptions on the smoothness and structure of the aposteriori probability a rate of convergence is shown which is independent of the dimension of the image. This proves that in image classification it is possible to circumvent the curse of dimensionality by convolutional neural networks.
Keywords
Cite
@article{arxiv.2003.01526,
title = {On the rate of convergence of image classifiers based on convolutional neural networks},
author = {M. Kohler and A. Krzyzak and B. Walter},
journal= {arXiv preprint arXiv:2003.01526},
year = {2020}
}