An Integral Upper Bound for Neural Network Approximation

DOI10.1162/neco.2009.04-08-745zbMath1186.68370OpenAlexW1987961932WikidataQ48503903 ScholiaQ48503903MaRDI QIDQ3399370

Paul C. Kainen, Vera Kurková

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

zbMATH Keywords

perceptron networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Approximation theorems for a family of multivariate neural network operators in Orlicz-type spaces ⋮ Approximation by max-product neural network operators of Kantorovich type ⋮ Saturation classes for MAX-product neural network operators activated by sigmoidal functions ⋮ Complexity estimates based on integral transforms induced by computational units ⋮ Convergence results for a family of Kantorovich max-product neural network operators in a multivariate setting ⋮ Convergence for a family of neural network operators in Orlicz spaces ⋮ Asymptotic expansion for neural network operators of the Kantorovich type and high order of approximation ⋮ Piecewise convexity of artificial neural networks ⋮ The construction and approximation of the neural network with two weights

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Complexity of Gaussian-radial-basis networks approximating smooth functions
• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• Rates of convex approximation in non-Hilbert spaces
• Approximation and learning of convex superpositions
• A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves
• Universal approximation bounds for superpositions of a sigmoidal function
• Error Estimates for Approximate Optimization by the Extended Ritz Method

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