Neural Networks with Local Receptive Fields and Superlinear VC Dimension

DOI10.1162/089976602317319018MaRDI QIDQ4330677zbMATH OpenOpenAlexWikidataFDO

Authors Michael Schmitt

Publication date 14 May 2002

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/089976602317319018

zbMATH Keywords

radial basis functionRBF neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• scientific article; zbMATH DE number 1804095
• scientific article; zbMATH DE number 1843045
• Neural Nets with Superlinear VC-Dimension
• Vapnik-Chervonenkis dimension of recurrent neural networks
• scientific article; zbMATH DE number 759415

Cites work

• Balls in \(\mathbb{R}^k\) do not cut all subsets of \(k+2\) points
• Classification by polynomial surfaces
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Density and dimension
• Enumeration of Seven-Argument Threshold Functions
• Exact VC-dimension of Boolean monomials
• Learnability and the Vapnik-Chervonenkis dimension
• Neural Nets with Superlinear VC-Dimension
• Neural networks with quadratic VC dimension
• On the complexity of learning for spiking neurons with temporal coding.
• Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks
• Sample sizes for threshold networks with equivalences
• Some special Vapnik-Chervonenkis classes

Cited in

(4)

• scientific article; zbMATH DE number 1804095 (Why is no real title available?)
• Neural Nets with Superlinear VC-Dimension
• On the Capabilities of Higher-Order Neurons: A Radial Basis Function Approach
• Descartes' Rule of Signs for Radial Basis Function Neural Networks

This page was built for publication: Neural Networks with Local Receptive Fields and Superlinear VC Dimension

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4330677)