Covering numbers for support vector machines

Support vector (SV) machines are linear classifiers that use the maximum margin hyperplane in a feature space defined by a kernel function. Previously, the only bounds on the generalization performance of SV machines (within Valiant's probably approximately correct framework) took no account of...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on information theory 2002-01, Vol.48 (1), p.239-250
Hauptverfasser:	Ying Guo, Bartlett, P.L., Shawe-Taylor, J., Williamson, R.C.
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Covering Decay rate Eigenvalues Errors Gaussian Integral equations Kernels Mathematical analysis Support vector machines Vectors (mathematics)
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!