A Note on the Generalization Performance of Kernel Classifiers with Margin

dc.creator	Evgeniou, Theodoros
dc.creator	Pontil, Massimiliano
dc.date	2004-10-20T20:48:37Z
dc.date	2004-10-20T20:48:37Z
dc.date	2000-05-01
dc.date.accessioned	2013-10-09T02:48:25Z
dc.date.available	2013-10-09T02:48:25Z
dc.date.issued	2013-10-09
dc.identifier	AIM-1681
dc.identifier	CBCL-184
dc.identifier	http://hdl.handle.net/1721.1/7169
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description	We present distribution independent bounds on the generalization misclassification performance of a family of kernel classifiers with margin. Support Vector Machine classifiers (SVM) stem out of this class of machines. The bounds are derived through computations of the $V_gamma$ dimension of a family of loss functions where the SVM one belongs to. Bounds that use functions of margin distributions (i.e. functions of the slack variables of SVM) are derived.
dc.format	9 p.
dc.format	1149066 bytes
dc.format	253797 bytes
dc.format	application/postscript
dc.format	application/pdf
dc.language	en_US
dc.relation	AIM-1681
dc.relation	CBCL-184
dc.subject	AI
dc.subject	MIT
dc.subject	Artificial Intelligence
dc.subject	missing data
dc.subject	mixture models
dc.subject	statistical learning
dc.subject	EM algorithm
dc.subject	neural networks
dc.subject	kernel classifiers
dc.subject	Support Vector Machine
dc.subject	regularization networks
dc.subject	statistical learning theory
dc.subject	V-gamma dimension.
dc.title	A Note on the Generalization Performance of Kernel Classifiers with Margin

Files in this item

Files	Size	Format	View
There are no files associated with this item.