Higher Order Orthogonal Polynomials as Activation Functions in Artificial Neural Networks

DOI10.55630/SJC.2023.17.1-16MaRDI QIDQ6136053FDOQ6136053

Authors:

Publication date: 28 August 2023

Published in: Serdica Journal of Computing (Search for Journal in Brave)

Recommendations

• scientific article; zbMATH DE number 1954154
• Properties and performance of orthogonal neural network in function approximation
• Orthogonal considerations in the design of neural networks for function approximation.
• On function recovery by neural networks based on orthogonal expansions
• A functional equation with polynomial solutions and application to neural networks
• Hölder continuous activation functions in neural networks
• Simultaneous Approximations of Polynomials and Derivatives and Their Applications to Neural Networks

zbMATH Keywords

artificial neural networksactivation functionHermite orthogonal polynomialsChebyshev orthogonal polynomials

Mathematics Subject Classification ID

Computation of special functions and constants, construction of tables (65D20) Artificial neural networks and deep learning (68T07) Orthogonal polynomials and functions of hypergeometric type (Jacobi, Laguerre, Hermite, Askey scheme, etc.) (33C45)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)

This page was built for publication: Higher Order Orthogonal Polynomials as Activation Functions in Artificial Neural Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6136053)