Approximation analysis of CNNs from a feature extraction view

DOI10.1142/S0219530524500015MaRDI QIDQ6496341

Ding-Xuan Zhou, Jianfei Li, Han Feng

Publication date: 3 May 2024

Published in: Analysis and Applications (Singapore) (Search for Journal in Brave)

zbMATH Keywords

feature extractionapproximation theoryconvolutional neural networksdeep learning2D convolution

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Computing methodologies for image processing (68U10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Cites Work

• Unnamed Item
• Robust signal processing for wireless communications
• Random projections of smooth manifolds
• Approximation properties of a multilayered feedforward artificial neural network
• Theory of deep convolutional neural networks. II: Spherical analysis
• Approximation properties of deep ReLU CNNs
• Theory of deep convolutional neural networks: downsampling
• Error bounds for approximations with deep ReLU networks
• Universality of deep convolutional neural networks
• Approximation by Combinations of ReLU and Squared ReLU Ridge Functions With <inline-formula> <tex-math notation="LaTeX">$\ell^1$ </tex-math> </inline-formula> and <inline-formula> <tex-math notation="LaTeX">$\ell^0$ </tex-math> </inline-formula> Controls
• Neural Networks and Deep Learning
• Optimal Approximation with Sparsely Connected Deep Neural Networks
• High-Dimensional Data Analysis with Low-Dimensional Models
• Deep Network Approximation Characterized by Number of Neurons
• A Fast Learning Algorithm for Deep Belief Nets
• Approximating functions with multi-features by deep convolutional neural networks
• Theory of deep convolutional neural networks. III: Approximating radial functions

This page was built for publication: Approximation analysis of CNNs from a feature extraction view