Title: A generic model of multi-class support vector machine

Authors: Yann Guermeur

Addresses: LORIA-CNRS, Campus Scientifique, BP 239, 54506 Vandoeuvre-lès-Nancy Cedex, France

Abstract: Roughly speaking, there is one main model of pattern recognition support vector machine, with several variants of lower popularity. On the contrary, among the different multi-class support vector machines which can be found in literature, none is clearly favoured. On the one hand, they exhibit distinct statistical properties. On the other hand, multiple comparative studies between multi-class support vector machines and decomposition methods have highlighted the fact that in practice, each model has its advantages and drawbacks. In this article, we introduce a generic model of multi-class support vector machine. It provides the first unifying definition of all the machines of this kind published so far. This contribution makes it possible to devise new machines meeting specific requirements as well as to analyse globally the statistical properties of the multi-class support vector machines.

Keywords: multi-class SVM; support vector machines; M-SVMs; model selection; modelling.

DOI: 10.1504/IJIIDS.2012.050094

International Journal of Intelligent Information and Database Systems, 2012 Vol.6 No.6, pp.555 - 577

Received: 03 Mar 2012
Accepted: 06 Mar 2012
Published online: 23 Aug 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article