Uniform approximation by neural networks

DOI10.1006/jath.1997.3217zbMath0932.41016OpenAlexW2026307262MaRDI QIDQ1273409

Yu. I. Makovoz

Publication date: 8 March 2000

Published in: Journal of Approximation Theory (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/jath.1997.3217

zbMATH Keywords

neural networksindependent random variablesactivation functiontarget function

Mathematics Subject Classification ID

Abstract approximation theory (approximation in normed linear spaces and other abstract spaces) (41A65) Approximation by other special function classes (41A30) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46) Research exposition (monographs, survey articles) pertaining to approximations and expansions (41-02)

Related Items (50)

On Approximation by Neural Networks with Optimized Activation Functions and Fixed Weights ⋮ Approximation theorems for a family of multivariate neural network operators in Orlicz-type spaces ⋮ Approximation by max-product neural network operators of Kantorovich type ⋮ Approximation by ridge function fields over compact sets ⋮ Approximation by network operators with logistic activation functions ⋮ Max-product neural network and quasi-interpolation operators activated by sigmoidal functions ⋮ Multivariate Jackson-type inequality for a new type neural network approximation ⋮ The estimate for approximation error of spherical neural networks ⋮ A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves ⋮ The errors of approximation for feedforward neural networks in thelpmetric ⋮ Uniform approximation rates and metric entropy of shallow neural networks ⋮ Neural network interpolation operators activated by smooth ramp functions ⋮ Neural network operators: constructive interpolation of multivariate functions ⋮ On the tractability of multivariate integration and approximation by neural networks ⋮ Approximation by neural networks with sigmoidal functions ⋮ Voronovskaja type theorems and high-order convergence neural network operators with sigmoidal functions ⋮ Saturation classes for MAX-product neural network operators activated by sigmoidal functions ⋮ Modified neural network operators and their convergence properties with summability methods ⋮ Pointwise and uniform approximation by multivariate neural network operators of the max-product type ⋮ Construction and approximation for a class of feedforward neural networks with sigmoidal function ⋮ Approximation by neural networks with a bounded number of nodes at each level ⋮ Neural network interpolation operators optimized by Lagrange polynomial ⋮ Characterization of the variation spaces corresponding to shallow neural networks ⋮ A comparison between fixed-basis and variable-basis schemes for function approximation and functional optimization ⋮ Convergence results for a family of Kantorovich max-product neural network operators in a multivariate setting ⋮ Neural network approximation and estimation of classifiers with classification boundary in a Barron class ⋮ The construction and approximation of feedforward neural network with hyperbolic tangent function ⋮ Convergence for a family of neural network operators in Orlicz spaces ⋮ Essential rate for approximation by spherical neural networks ⋮ The errors of simultaneous approximation of multivariate functions by neural networks ⋮ Approximation results for neural network operators activated by sigmoidal functions ⋮ Multivariate neural network operators with sigmoidal activation functions ⋮ Minimization of Error Functionals over Perceptron Networks ⋮ Approximation by neural networks with weights varying on a finite set of directions ⋮ Unnamed Item ⋮ Interpolation by neural network operators activated by ramp functions ⋮ Convergence of a family of neural network operators of the Kantorovich type ⋮ Multivariate sigmoidal neural network approximation ⋮ The approximation operators with sigmoidal functions ⋮ Asymptotic expansion for neural network operators of the Kantorovich type and high order of approximation ⋮ Optimization based on quasi-Monte Carlo sampling to design state estimators for non-linear systems ⋮ Piecewise convexity of artificial neural networks ⋮ Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions ⋮ Quantitative approximation by perturbed Kantorovich-Choquet neural network operators ⋮ Rates of approximation by neural network interpolation operators ⋮ On sharpness of error bounds for univariate approximation by single hidden layer feedforward neural networks ⋮ Approximation by perturbed neural network operators ⋮ Rates of minimization of error functionals over Boolean variable-basis functions ⋮ Approximations by multivariate perturbed neural network operators ⋮ A New Function Space from Barron Class and Application to Neural Network Approximation

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• On trigonometric n-widths and their generalization
• Nonlinear approximation by trigonometric sums
• Random approximants and neural networks
• Universal approximation bounds for superpositions of a sigmoidal function
• Decomposition theorems and approximation by a “floating" system of exponentials
• Sup-norm approximation bounds for networks through probabilistic methods
• Lower Bounds for Approximation by Nonlinear Manifolds
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities

This page was built for publication: Uniform approximation by neural networks