Approximation error of single hidden layer neural networks with fixed weights

DOI10.1016/J.IPL.2023.106467MaRDI QIDQ6195340zbMATH OpenOpenAlexFDO

Authors Vugar E. Ismailov

Publication date 13 March 2024

Published in Information Processing Letters (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2202.03289

zbMATH Keywords

approximation algorithmsapproximation errormean periodic functionneural networkpath

Mathematics Subject Classification ID

Theory of computing (68Qxx)

Abstract: This paper provides an explicit formula for the approximation error of single hidden layer neural networks with two fixed weights.

Cites work

• A note on the equioscillation theorem for best ridge function approximation
• Approximation by a sum of two algebras. The lightning bolt principle
• Approximation by neural networks with scattered data
• Approximation by neural networks with weights varying on a finite set of directions
• Approximation by Ridge functions and neural networks with one hidden layer
• Approximation by Solutions of the Planar Wave Equation
• Approximation by superpositions of a sigmoidal function
• Approximation results for neural network operators activated by sigmoidal functions
• Deep learning
• Degree of approximation by neural and translation networks with a single hidden layer
• Extension of localised approximation by neural networks
• scientific article; zbMATH DE number 1405266 (Why is no real title available?)
• scientific article; zbMATH DE number 3217133 (Why is no real title available?)
• scientific article; zbMATH DE number 964891 (Why is no real title available?)
• Interpolation by Ridge functions
• Interpolation on lines by ridge functions
• Jackson-type inequalities for spherical neural networks with doubling weights
• Lectures on mean periodic functions. Notes by P. K. Raman
• Lower bounds for approximation by MLP neural networks
• Measure Theoretic Results for Approximation by Neural Networks with Limited Weights
• Multilayer feedforward networks are universal approximators
• On functions of three variables
• On functions which are mean periodic on a half-line
• On the approximation by single hidden layer feedforward neural networks with fixed weights
• On the approximation of a function of several variables by the sum of functions of fewer variables
• On the proximinality of ridge functions
• Ridge functions and applications in neural networks
• Ridgelets: estimating with ridge functions
• Saturation classes for MAX-product neural network operators activated by sigmoidal functions
• Some properties of mean periodic functions
• The Degree of Approximation of Certain Functions of Two Variables by a Sum of Functions of One Variable
• Théorie générale des fonctions moyenne-périodiques
• Uniform approximation by real functions
• Universal approximation bounds for superpositions of a sigmoidal function

Cited in

(3)

• Nonlinear complex dynamical systems modeling and adaptive control based on a novel diagonally expanded functional link neural network (DEFLNN)
• Approximation with RBF neural networks using unit smoothing factors and translations
• On the approximation by RBF neural networks with translations

This page was built for publication: Approximation error of single hidden layer neural networks with fixed weights

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6195340)