PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A note on the bias in SVMs for multi-classification
Luis Gonzalez-Abril, Cecilio Angulo, Francisco Velasco and Juan Antonio Ortega
IEEE Transactions on Neural Networks, vol. 19, no. 4, pp. 723-725 Volume 19, Number 4, pp. 723-725, 2008. ISSN 1045-9227

Abstract

During the usual SVM biclassification learning process, the bias is chosen a posteriori as the value halfway between separating hyperplanes. A note on different approaches on the calculation of the bias when SVM is used for multiclassification is provided and empirical experimentation is carried out which shows that the accuracy rate can be improved by using bias formulations, although no single formulation stands out as providing better performance.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:4528
Deposited By:Cecilio Angulo
Deposited On:13 March 2009