Complexity of Gaussian-radial-basis networks approximating smooth functions

DOI10.1016/J.JCO.2008.08.001zbMATH Open1162.65006OpenAlexW1979554434MaRDI QIDQ998978FDOQ998978

Authors: Paul C. Kainen, Marcello Sanguineti, Věra Kůrková 

Publication date: 30 January 2009

Published in: Journal of Complexity (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jco.2008.08.001

Recommendations

• The rate of approximation of Gaussian radial basis neural networks in continuous function space
• Gaussian radial basis functions and inner product spaces.
• scientific article; zbMATH DE number 1843036
• Gaussian radial basis functions and the approximation of input-output maps
• Almost optimal estimates for approximation and learning by radial basis function networks

zbMATH Keywords

model complexityrates of approximationmultivariable approximationapproximate smooth functionsBessel and Sobolev normsGaussian-radial-basis-function networkstractability of approximationvariation norms

Mathematics Subject Classification ID

Multidimensional problems (41A63) Algorithms for approximation of functions (65D15)

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
• Comparison of worst case errors in linear and neural network approximation
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Tractability and strong tractability of linear multivariate problems
• Real Interpolation of Sobolev Spaces on Subdomains of Rn
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• On best approximation by ridge functions
• Error bounds for approximation with neural networks
• Approximation by superposition of sigmoidal and radial basis functions
• Title not available (Why is that?)
• Sobolev error estimates and a Bernstein inequality for scattered data interpolation via radial basis functions
• Complexity of weighted approximation over \(\mathbb{R}^d\)
• Title not available (Why is that?)
• On the tractability of multivariate integration and approximation by neural networks
• Title not available (Why is that?)
• Dimension-independent bounds on the degree of approximation by neural networks
• When is approximation by Gaussian networks necessarily a linear process?
• Minimization of Error Functionals over Perceptron Networks

Cited In (22)

• New insights into Witsenhausen's counterexample
• Can dictionary-based computational models outperform the best linear ones?
• Some comparisons of complexity in dictionary-based and linear computational models
• The rate of approximation of Gaussian radial basis neural networks in continuous function space
• Title not available (Why is that?)
• Suboptimal solutions to dynamic optimization problems via approximations of the policy functions
• Complexity of Shallow Networks Representing Finite Mappings
• Error estimates of quasi-interpolation and its derivatives
• Estimates of variation with respect to a set and applications to optimization problems
• Accuracy of approximations of solutions to Fredholm equations by kernel methods
• Approximation schemes for functional optimization problems
• Lower bounds for artificial neural network approximations: a proof that shallow neural networks fail to overcome the curse of dimensionality
• Comparing fixed and variable-width Gaussian networks
• A comment on ``Relaxed conditions for radial-basis function networks to be universal approximators
• Learning-based complexity evaluation of radial basis function networks
• Probabilistic lower bounds for approximation by shallow perceptron networks
• Two fast and accurate heuristic RBF learning rules for data classification
• Complexity estimates based on integral transforms induced by computational units
• Title not available (Why is that?)
• Dynamic programming and value-function approximation in sequential decision problems: error analysis and numerical results
• An Integral Upper Bound for Neural Network Approximation
• Wavelet neural networks functional approximation and application

This page was built for publication: Complexity of Gaussian-radial-basis networks approximating smooth functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q998978)