On the rate of convergence of image classifiers based on convolutional neural networks

DOI10.1007/s10463-022-00828-4OpenAlexW3009393055MaRDI QIDQ2087403

Michael Kohler, Benjamin Walter, Adam Krzyżak

Publication date: 20 October 2022

Published in: Annals of the Institute of Statistical Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2003.01526

zbMATH Keywords

rate of convergencecurse of dimensionalityimage classificationconvolutional neural networks

Mathematics Subject Classification ID

Statistics (62-XX)

Uses Software

• CIFAR
• ImageNet
• AlexNet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• AlexNet
• Minimax theory of image reconstruction
• Maximum likelihood features for generative image models
• A distribution-free theory of nonparametric regression
• Over-parametrized deep neural networks minimizing the empirical risk do not generalize well
• On the rate of convergence of fully connected deep neural network regression estimates
• Nonparametric regression using deep neural networks with ReLU activation function
• Universality of deep convolutional neural networks
• On deep learning as a remedy for the curse of dimensionality in nonparametric regression
• Necessary and sufficient conditions for the pointwise convergence of nearest neighbor regression function estimates
• Equivalence of approximation by convolutional neural networks and fully-connected networks
• Nonparametric Regression Based on Hierarchical Interaction Models
• Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review
• Fast convergence rates of deep neural networks for classification