A convergent deep learning algorithm for approximation of polynomials

DOI10.5802/CRMATH.462MaRDI QIDQ6073137zbMATH OpenOpenAlexFDO

Authors Bruno Després

Publication date 15 September 2023

Published in Comptes Rendus. Mathématique. Académie des Sciences, Paris (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.5802/crmath.462

Mathematics Subject Classification ID

Numerical methods for functional equations (65Q20) Computer aspects of numerical algorithms (65Y99) Neural and heuristic methods applied to problems in optics and electromagnetic theory (78M32)

Cites work

• A functional equation with polynomial solutions and application to neural networks
• Better approximations of high dimensional smooth functions by deep neural networks with rectified power units
• Deep learning
• Deep ReLU networks and high-order finite element methods
• Error bounds for approximations with deep ReLU networks
• scientific article; zbMATH DE number 439380 (Why is no real title available?)
• scientific article; zbMATH DE number 477682 (Why is no real title available?)
• Neural networks and numerical analysis
• Nonlinear approximation and (deep) ReLU networks
• ReLU deep neural networks and linear finite elements
• Representation formulas and pointwise properties for Barron functions
• The Takagi function and its generalization

Cited in

(2)

• scientific article; zbMATH DE number 1453041 (Why is no real title available?)
• A posteriori Lipschitz bounds for deep neural networks

This page was built for publication: A convergent deep learning algorithm for approximation of polynomials

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6073137)