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

DOI10.1007/S10463-022-00828-4MaRDI QIDQ2087403zbMATH OpenOpenAlexFDO

Authors Michael Kohler, Adam Krzyżak, Benjamin Walter

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

convolutional neural networkscurse of dimensionalityimage classificationrate of convergence

Mathematics Subject Classification ID

Statistics (62-XX)

Cites work

• A distribution-free theory of nonparametric regression
• AlexNet
• Deep convolutional neural networks for image classification: a comprehensive review
• Deep learning
• Equivalence of approximation by convolutional neural networks and fully-connected networks
• Fast convergence rates of deep neural networks for classification
• scientific article; zbMATH DE number 893887 (Why is no real title available?)
• scientific article; zbMATH DE number 7064043 (Why is no real title available?)
• Maximum likelihood features for generative image models
• Minimax theory of image reconstruction
• Necessary and sufficient conditions for the pointwise convergence of nearest neighbor regression function estimates
• Nonparametric Regression Based on Hierarchical Interaction Models
• Nonparametric regression using deep neural networks with ReLU activation function
• On deep learning as a remedy for the curse of dimensionality in nonparametric regression
• On the rate of convergence of fully connected deep neural network regression estimates
• Over-parametrized deep neural networks minimizing the empirical risk do not generalize well
• Universality of deep convolutional neural networks

Cited in

(6)

• Statistical theory for image classification using deep convolutional neural network with cross-entropy loss under the hierarchical max-pooling model
• Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent
• Deep approximate policy iteration
• Misclassification bounds for PAC-Bayesian sparse deep learning
• Physics-guided inverse regression for crop quality assessment
• A novel statistical approach to analyze image classification

Describes a project that uses

Uses Software

• AlexNet
• ImageNet
• CIFAR

This page was built for publication: On the rate of convergence of image classifiers based on convolutional neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2087403)