Comparing fixed and variable-width Gaussian networks

DOI10.1016/J.NEUNET.2014.05.005zbMath1343.68200OpenAlexW2080633186WikidataQ51081782 ScholiaQ51081782MaRDI QIDQ889280

Paul C. Kainen, Vera Kurková

Publication date: 6 November 2015

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

Full work available at URL: https://doi.org/10.1016/j.neunet.2014.05.005

zbMATH Keywords

universal approximatorsargminima of error functionalsfunctionally equivalent networksGaussian radial and kernel networksstabilizers defined by Gaussian kernels

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Multidimensional problems (41A63)

Related Items (2)

Radial fuzzy systems ⋮ Robust Training of Radial Basis Function Neural Networks

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Networks and the best approximation property
• Complexity of Gaussian-radial-basis networks approximating smooth functions
• When is approximation by Gaussian networks necessarily a linear process?
• Support-vector networks
• Singularities of finite scaling functions
• A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves
• On the mathematical foundations of learning
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• Support Vector Machines
• Descartes' Rule of Signs for Radial Basis Function Neural Networks

This page was built for publication: Comparing fixed and variable-width Gaussian networks