Function approximation on non-Euclidean spaces

DOI10.1016/j.neunet.2004.09.003zbMath1085.68124OpenAlexW2025259401WikidataQ51980328 ScholiaQ51980328MaRDI QIDQ1763473

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

zbMATH Keywords

InvariantsRegularizationFeed-forward neural networksFunction approximationNon-metric spaces

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items

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

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Interpolation of scattered data: distance matrices and conditionally positive definite functions
• Networks and the best approximation property
• Genetic algorithms and very fast simulated reannealing: A comparison
• The Hyperbell algorithm for global optimization: A random walk using Cauchy densities
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• An Extension of the String-to-String Correction Problem
• Dynamic programming algorithm optimization for spoken word recognition
• The String-to-String Correction Problem
• Learning representations by back-propagating errors
• Approximation by superpositions of a sigmoidal function
• Interpolation by radial functions on Sobolev space