Universal Consistency of Deep Convolutional Neural Networks

DOI10.1109/TIT.2022.3151753MaRDI QIDQ5088579zbMATH OpenOpenAlexFDO

Authors Kai-Dong Wang, Yao Wang, Ding-Xuan Zhou, Shaobo Lin

Publication date 13 July 2022

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2106.12498

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Cited in

(9)

• Approximation properties of deep ReLU CNNs
• scientific article; zbMATH DE number 1294021 (Why is no real title available?)
• Strong universal consistency of neural network classifiers
• Learning ability of interpolating deep convolutional neural networks
• On the rates of convergence for learning with convolutional neural networks
• Optimal rates of approximation by shallow \(\operatorname{ReLU}^k\) neural networks and applications to nonparametric regression
• On the universal approximation property of deep fully convolutional neural networks
• DUM-Net: a model-driven unrolled framework for multi-modal image registration
• Higher-order approximation rates for ReLU CNNs in Korobov spaces

This page was built for publication: Universal Consistency of Deep Convolutional Neural Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5088579)