Cross-validation based weights and structure determination of Chebyshev-polynomial neural networks for pattern classification

DOI10.1016/J.PATCOG.2014.04.026MaRDI QIDQ1676889zbMATH OpenOpenAlexFDO

Authors Yonghua Yin, Xiaotian Yu, Lin Xiao, Yunong Zhang, Dong-Sheng Guo

Publication date 10 November 2017

Published in Pattern Recognition (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.patcog.2014.04.026

zbMATH Keywords

robustnesscross validationneural networkChebyshev polynomialpattern classification

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) Orthogonal polynomials and functions of hypergeometric type (Jacobi, Laguerre, Hermite, Askey scheme, etc.) (33C45)

Recommendations

• A new algorithm for training neural networks based on generalized Chebyshev polynomials
• scientific article; zbMATH DE number 529801
• Polynomial-based radial basis function neural networks (P-RBF NNs) realized with the aid of particle swarm optimization
• Parameter redundancy in neural networks: an application of Chebyshev polynomials
• Design of radial basis function classifier based on polynomial neural networks

Cites work

• scientific article; zbMATH DE number 1392848 (Why is no real title available?)
• A survey of cross-validation procedures for model selection
• Extension of Bernstein polynomials to infinite dimensional case
• Machine learning for first-order theorem proving
• Multi-class pattern classification using neural networks
• Orthogonal polynomials of several variables
• Pattern classification by linear goal programming and its extensions
• The Predictive Sample Reuse Method with Applications
• Using Chebyshev polynomials to approximate partial differential equations

Cited in

(5)

• Multi-variable regression methods using modified Chebyshev polynomials of class 2
• A new algorithm for training neural networks based on generalized Chebyshev polynomials
• Multi-input bio-inspired weights and structure determination neuronet with applications in European central bank publications
• Random neural network methods and deep learning
• Toward deep neural networks: Mirror extreme learning machines for pattern classification

Describes a project that uses

Uses Software

• LIBSVM
• UCI

This page was built for publication: Cross-validation based weights and structure determination of Chebyshev-polynomial neural networks for pattern classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1676889)