A functional equation with polynomial solutions and application to neural networks

DOI10.5802/crmath.124zbMath1459.65236OpenAlexW4385713603MaRDI QIDQ2219991

Matthieu Ancellin, Bruno Després

Publication date: 21 January 2021

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

Full work available at URL: https://doi.org/10.5802/crmath.124

zbMATH Keywords

neural networksfunctional equationsrecursive neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Computer aspects of numerical algorithms (65Y99) Numerical methods for functional equations (65Q20)

Related Items (1)

A convergent deep learning algorithm for approximation of polynomials

Uses Software

• ForwardDiff
• Optim

Cites Work

• Unnamed Item
• Unnamed Item
• Weierstrass' function and chaos
• Nonlinear approximation and (deep) ReLU networks
• Machine learning design of volume of fluid schemes for compressible flows
• Error bounds for approximations with deep ReLU networks
• Relu Deep Neural Networks and Linear Finite Elements
• The Takagi function and its generalization
• Machine Learning and Control Theory
• Deep ReLU networks and high-order finite element methods
• Better Approximations of High Dimensional Smooth Functions by Deep Neural Networks with Rectified Power Units
• Approximation by superpositions of a sigmoidal function

This page was built for publication: A functional equation with polynomial solutions and application to neural networks