An Integral Upper Bound for Neural Network Approximation

DOI10.1162/NECO.2009.04-08-745zbMATH Open1186.68370DBLPjournals/neco/KainenK09OpenAlexW1987961932WikidataQ48503903 ScholiaQ48503903MaRDI QIDQ3399370FDOQ3399370

Authors: Paul C. Kainen, Věra Kůrková 

Publication date: 12 October 2009

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: http://www.nusl.cz/ntk/nusl-39633

Recommendations

• scientific article; zbMATH DE number 1843047
• scientific article; zbMATH DE number 1784858
• scientific article; zbMATH DE number 2112349
• Universal approximation bounds for superpositions of a sigmoidal function
• Geometric Rates of Approximation by Neural Networks

zbMATH Keywords

perceptron networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• Universal approximation bounds for superpositions of a sigmoidal function
• Title not available (Why is that?)
• Title not available (Why is that?)
• Error Estimates for Approximate Optimization by the Extended Ritz Method
• Rates of convex approximation in non-Hilbert spaces
• Complexity of Gaussian-radial-basis networks approximating smooth functions
• Approximation and learning of convex superpositions
• A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves
• Title not available (Why is that?)

Cited In (18)

• A tight upper bound on the generalization error of feedforward neural networks
• Integral combinations of Heavisides
• Continuous limits of residual neural networks in case of large input data
• Title not available (Why is that?)
• The construction and approximation of the neural network with two weights
• Approximation theorems for a family of multivariate neural network operators in Orlicz-type spaces
• Convergence for a family of neural network operators in Orlicz spaces
• Approximation by max-product neural network operators of Kantorovich type
• Asymptotic expansion for neural network operators of the Kantorovich type and high order of approximation
• Piecewise convexity of artificial neural networks
• On the tractability of multivariate integration and approximation by neural networks
• Lower bounds for artificial neural network approximations: a proof that shallow neural networks fail to overcome the curse of dimensionality
• Title not available (Why is that?)
• Complexity estimates based on integral transforms induced by computational units
• Measure Theoretic Results for Approximation by Neural Networks with Limited Weights
• Convergence results for a family of Kantorovich max-product neural network operators in a multivariate setting
• Saturation classes for MAX-product neural network operators activated by sigmoidal functions
• A Framework for the Construction of Upper Bounds on the Number of Affine Linear Regions of ReLU Feed-Forward Neural Networks

This page was built for publication: An Integral Upper Bound for Neural Network Approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3399370)