\(L^p\) approximation capability of RBF neural networks

DOI10.1007/S10114-008-6423-XzbMath1169.68578OpenAlexW2019750728MaRDI QIDQ944076

Wei Wu, Jin Ling Long, Dong Nan, Yu Mei Ma, Lin Jun Sun

Publication date: 12 September 2008

Published in: Acta Mathematica Sinica. English Series (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10114-008-6423-x

zbMATH Keywords

neural networksradial basis function\(L^p\) approximation capability

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Approximation by rational functions (41A20)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Approximation by superposition of sigmoidal and radial basis functions
• On simultaneous approximations by radial basis function neural networks
• Relaxed conditions for radial-basis function networks to be universal approximators.
• TDI-subspaces of \(C(\mathbb{R}^ d)\) and some density problems from neural networks
• Denseness of radial-basis functions in \(L^ 2(R^ n)\) and its applications in neural networks
• Universal approximation capability of EBF neural networks with arbitrary activation functions
• Approximation by superpositions of a sigmoidal function

This page was built for publication: \(L^p\) approximation capability of RBF neural networks