PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Unified dual for bi-class svm approaches
Luis Gonzalez, Cecilio Angulo, Francisco Velasco and Andreu Catala
Pattern Recognition Volume 38, Number 10, pp. 1772-1774, 2005. ISSN 0031-3203

Abstract

SVM theory was originally developed on the basis of a separable binary classification problem, and other approaches have been later introduced. In this paper, we demonstrated that all these approaches admit the same dual problem formulation.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:2222
Deposited By:Cecilio Angulo
Deposited On:01 October 2006