Hyper-parameter selection for sparse LS-SVM via minimization of its localized generalization error

DOI10.1142/S0219691313500306zbMATH Open1270.68253OpenAlexW2152721295MaRDI QIDQ2846508FDOQ2846508

Authors: Binbin Sun, Wing W. Y. Ng, Daniel S. Yeung, Patrick P. K. Chan 

Publication date: 5 September 2013

Published in: International Journal of Wavelets, Multiresolution and Information Processing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1142/s0219691313500306

Recommendations

• Advances in Neural Networks – ISNN 2005
• Selection methods for extended least squares support vector machines
• A selection method for hyper-parameters of support vector regression by chaotic cultural algorithm
• Practical selection of SVM parameters and noise estimation for SVM regression
• Efficient optimization of hyper-parameters for least squares support vector regression

zbMATH Keywords

sparsityleast squares support vector machine (LS-SVM)sensitivity measurehyper-parameter selectionlocalized generalization error model (L-GEM)

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Efficient leave-one-out cross-validation of kernel Fisher discriminant classifiers.
• Benchmarking least squares support vector machine classifiers
• Evolution strategies based adaptive \(L_{p}\) LS-SVM
• Efficient cross-validation for kernelized least-squares regression with sparse basis expansions
• Sparse kernel learning with LASSO and Bayesian inference algorithm
• Feature selection using localized generalization error for supervised classification problems using RBFNN

Cited In (3)

• LS-SVM regression for structural damage diagnosis using the iterated improved reduction system
• Advances in Neural Networks – ISNN 2005
• Structural damage diagnosis using incomplete static responses and LS-SVM

This page was built for publication: Hyper-parameter selection for sparse LS-SVM via minimization of its localized generalization error

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2846508)