Compactly Supported RBF Kernels for Sparsifying the Gram Matrix in LS-SVM Regression Models

Autor:	Johan A. K. Suykens, Bart De Moor, Bart Hamers
Rok vydání:	2002
Předmět:	Reduction (complexity) Support vector machine Nonlinear system Generalization Radial basis function kernel Chaotic Radial basis function Algorithm Mathematics Gramian matrix
Zdroj:	Artificial Neural Networks — ICANN 2002 ISBN: 9783540440741 ICANN
DOI:	10.1007/3-540-46084-5_117
Popis:	In this paper we investigate the use of compactly supported RBF kernels for nonlinear function estimation with LS-SVMs. The choice of compact kernels, recently proposed by Genton, may lead to computational improvements and memory reduction. Examples, however, illustrate that compactly supported RBF kernels may lead to severe loss in generalization performance for some applications, e.g. in chaotic time-series prediction. As a result, the usefulness of such kernels may be much more application dependent than the use of the RBF kernel.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::5cf0991fcace163e66684c53380f515a https://doi.org/10.1007/3-540-46084-5_117 Zobrazit plný text záznamu