When is approximation by Gaussian networks necessarily a linear process?

DOI10.1016/J.NEUNET.2004.04.001MaRDI QIDQ1886595zbMATH OpenOpenAlexWikidataFDO

Authors H. N. Mhaskar

Publication date 18 November 2004

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2004.04.001

zbMATH Keywords

Converse theoremsGaussian networksWeighted polynomial approximation Hermite polynomials

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• scientific article; zbMATH DE number 218695
• Constructive approximation by Gaussian neural networks
• Gaussian approximation of stochastic processes with the linear regression
• Publication:4943029
• Publication:4508878
• scientific article; zbMATH DE number 1054350

Cites work

• Bounds on rates of variable-basis and neural-network approximation
• Comparison of worst case errors in linear and neural network approximation
• scientific article; zbMATH DE number 4157171 (Why is no real title available?)
• scientific article; zbMATH DE number 3437452 (Why is no real title available?)
• scientific article; zbMATH DE number 1972818 (Why is no real title available?)
• scientific article; zbMATH DE number 823880 (Why is no real title available?)
• scientific article; zbMATH DE number 3246460 (Why is no real title available?)
• Interpolation of scattered data: distance matrices and conditionally positive definite functions
• Norm estimates for the inverses of a general class of scattered-data radial-function interpolation matrices
• On direct and converse theorems in the theory of weighted polynomial approximation
• On the representation of band limited functions using finitely many bits
• Optimal nonlinear approximation

Cited in

(17)

• A tribute to Géza Freud
• Applied harmonic analysis and data processing. Abstracts from the workshop held March 25--31, 2018
• The rate of approximation of Gaussian radial basis neural networks in continuous function space
• A direct approach for function approximation on data defined manifolds
• Approximation of Sobolev classes by polynomials and ridge functions
• Two fast and accurate heuristic RBF learning rules for data classification
• Deep vs. shallow networks: an approximation theory perspective
• Constructive approximation by Gaussian neural networks
• George Lorentz and inequalities in approximation
• Deep Nitsche Method: Deep Ritz Method with Essential Boundary Conditions
• Deep neural networks for rotation-invariance approximation and learning
• Applications of classical approximation theory to periodic basis function networks and computational harmonic analysis
• Interpolation and rates of convergence for a class of neural networks
• Oscillation of Fourier transforms and Markov-Bernstein inequalities
• Comparing fixed and variable-width Gaussian networks
• Eignets for function approximation on manifolds
• Complexity of Gaussian-radial-basis networks approximating smooth functions

This page was built for publication: When is approximation by Gaussian networks necessarily a linear process?

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1886595)