Rates of approximation by ReLU shallow neural networks

DOI10.1016/j.jco.2023.101784zbMath1524.68322arXiv2307.12461MaRDI QIDQ6062171

No author found.

Publication date: 30 November 2023

Published in: Journal of Complexity (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2307.12461

zbMATH Keywords

Hölder spacedeep learningshallow neural networksReLUrates of uniform approximation

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Rate of convergence, degree of approximation (41A25)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Minimum Sobolev norm interpolation with trigonometric polynomials on the torus
• Multilayer feedforward networks are universal approximators
• Function approximation with zonal function networks with activation functions analogous to the rectified linear unit functions
• Provable approximation properties for deep neural networks
• Optimal nonlinear approximation
• Approximation properties of a multilayered feedforward artificial neural network
• Weak convergence and empirical processes. With applications to statistics
• Theory of deep convolutional neural networks. II: Spherical analysis
• Modeling interactive components by coordinate kernel polynomial models
• Approximation of functions from korobov spaces by deep convolutional neural networks
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Theory of deep convolutional neural networks: downsampling
• Error bounds for approximations with deep ReLU networks
• Universality of deep convolutional neural networks
• On convergence and growth of partial sums of Fourier series
• Deep vs. shallow networks: An approximation theory perspective
• Universal approximation bounds for superpositions of a sigmoidal function
• Deep distributed convolutional neural networks: Universality
• 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
• Optimal Approximation with Sparsely Connected Deep Neural Networks
• New Error Bounds for Deep ReLU Networks Using Sparse Grids
• Learning theory of minimum error entropy under weak moment conditions
• Error bounds for approximations with deep ReLU neural networks in Ws,p norms
• Regularization schemes for minimum error entropy principle
• Thresholded spectral algorithms for sparse approximations
• Breaking the Curse of Dimensionality with Convex Neural Networks
• A Fast Learning Algorithm for Deep Belief Nets
• On the convergence of multiple Fourier series
• Approximation by superpositions of a sigmoidal function
• Theory of deep convolutional neural networks. III: Approximating radial functions