Function approximation on non-Euclidean spaces

DOI10.1016/J.NEUNET.2004.09.003zbMATH Open1085.68124OpenAlexW2025259401WikidataQ51980328 ScholiaQ51980328MaRDI QIDQ1763473FDOQ1763473

Authors: Pierre Courrieu 

Publication date: 22 February 2005

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

Full work available at URL: https://doi.org/10.1016/j.neunet.2004.09.003

Recommendations

• scientific article
• Multilayer feedforward networks are universal approximators
• Two-hidden-layer feed-forward networks are universal approximators: a constructive approach
• The universal approximation capabilities of cylindrical approximate identity neural networks
• Neural-network approximation of functions of several variables

zbMATH Keywords

RegularizationInvariantsFeed-forward neural networksFunction approximationNon-metric spaces

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Regularization algorithms for learning that are equivalent to multilayer networks
• Dynamic programming algorithm optimization for spoken word recognition
• Learning representations by back-propagating errors
• Title not available (Why is that?)
• Interpolation of scattered data: distance matrices and conditionally positive definite functions
• The String-to-String Correction Problem
• Approximation by superpositions of a sigmoidal function
• An Extension of the String-to-String Correction Problem
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Networks and the best approximation property
• Genetic algorithms and very fast simulated reannealing: A comparison
• Interpolation by radial functions on Sobolev space
• The Hyperbell algorithm for global optimization: A random walk using Cauchy densities

Cited In (6)

• Quick approximation of bivariate functions
• Feature selection and multi-kernel learning for sparse representation on a manifold
• Density codes and shape spaces
• Generalized extreme learning machine acting on a metric space
• The universal approximation capabilities of double \(2\pi\)-periodic approximate identity neural networks
• Universal approximation on metric spaces

This page was built for publication: Function approximation on non-Euclidean spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1763473)