Uniform approximation by neural networks

DOI10.1006/JATH.1997.3217zbMATH Open0932.41016OpenAlexW2026307262MaRDI QIDQ1273409FDOQ1273409

Authors: Yuly 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

Recommendations

• Sur certains systèmes d'équations fonctionnelles et l'approximation des fonctions continues.
• scientific article; zbMATH DE number 16536
• On approximation of functions of two variables by sums of the form \(\varphi (x) + \psi (y)\) in \(L_ p\) spaces \((1\leq p\leq\infty )\)
• Bounding separable recourse functions with limited distribution information
• scientific article; zbMATH DE number 3953479
• scientific article; zbMATH DE number 4026440
• Necessary conditions for uniqueness in \(L^ 1\)-approximation
• scientific article; zbMATH DE number 2189947
• Summability approximation theorems of double random variables
• Approximation properties of some means of Fourier series

zbMATH Keywords

neural networksindependent random variablesactivation functiontarget function

Mathematics Subject Classification ID

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

Cites Work

• Title not available (Why is that?)
• Universal approximation bounds for superpositions of a sigmoidal function
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Random approximants and neural networks
• Title not available (Why is that?)
• Lower Bounds for Approximation by Nonlinear Manifolds
• Nonlinear approximation by trigonometric sums
• Decomposition theorems and approximation by a “floating" system of exponentials
• Title not available (Why is that?)
• Sup-norm approximation bounds for networks through probabilistic methods
• On trigonometric n-widths and their generalization

Cited In (55)

• A New Function Space from Barron Class and Application to Neural Network Approximation
• Neural network approximation and estimation of classifiers with classification boundary in a Barron class
• Sharp Bounds on the Approximation Rates, Metric Entropy, and n-Widths of Shallow Neural Networks
• Weighted variation spaces and approximation by shallow ReLU networks
• Optimization based on quasi-Monte Carlo sampling to design state estimators for non-linear systems
• Interpolation by neural network operators activated by ramp functions
• Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions
• A comparison between fixed-basis and variable-basis schemes for function approximation and functional optimization
• Approximation by network operators with logistic activation functions
• Approximation theorems for a family of multivariate neural network operators in Orlicz-type spaces
• Rates of approximation by neural network interpolation operators
• Convergence for a family of neural network operators in Orlicz spaces
• Approximation results for neural network operators activated by sigmoidal functions
• Approximation by max-product neural network operators of Kantorovich type
• Neural network interpolation operators optimized by Lagrange polynomial
• The construction and approximation of feedforward neural network with hyperbolic tangent function
• Multivariate neural network operators with sigmoidal activation functions
• Voronovskaja type theorems and high-order convergence neural network operators with sigmoidal functions
• Approximation by perturbed neural network operators
• Multivariate Jackson-type inequality for a new type neural network approximation
• Asymptotic expansion for neural network operators of the Kantorovich type and high order of approximation
• Piecewise convexity of artificial neural networks
• Neural network interpolation operators activated by smooth ramp functions
• The approximation operators with sigmoidal functions
• Multivariate sigmoidal neural network approximation
• Univariate hyperbolic tangent neural network approximation
• The errors of approximation for feedforward neural networks in thelpmetric
• On the tractability of multivariate integration and approximation by neural networks
• Universal approximation with quadratic deep networks
• Pointwise and uniform approximation by multivariate neural network operators of the max-product type
• On Approximation by Neural Networks with Optimized Activation Functions and Fixed Weights
• Modified neural network operators and their convergence properties with summability methods
• Approximations by multivariate perturbed neural network operators
• Replacing points by compacta in neural network approximation
• Quantitative approximation by perturbed Kantorovich-Choquet neural network operators
• 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
• Uniform approximation rates and metric entropy of shallow neural networks
• Neural network operators: constructive interpolation of multivariate functions
• Essential rate for approximation by spherical neural networks
• Title not available (Why is that?)
• The errors of simultaneous approximation of multivariate functions by neural networks
• On sharpness of error bounds for univariate approximation by single hidden layer feedforward neural networks
• Convergence of a family of neural network operators of the Kantorovich type
• Approximation by neural networks with weights varying on a finite set of directions
• The estimate for approximation error of spherical neural networks
• Max-product neural network and quasi-interpolation operators activated by sigmoidal functions
• Convergence results for a family of Kantorovich max-product neural network operators in a multivariate setting
• Characterization of the variation spaces corresponding to shallow neural networks
• Minimization of Error Functionals over Perceptron Networks
• Saturation classes for MAX-product neural network operators activated by sigmoidal functions
• Approximation by neural networks with sigmoidal functions
• Approximation by ridge function fields over compact sets
• Rates of minimization of error functionals over Boolean variable-basis functions
• A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1273409)