VC Theory of Large Margin Multi-Category Classifiers

  • Yann Guermeur
  • Published 2007 in Journal of Machine Learning Research

Abstract

In the context of discriminant analysis, Vapnik’s statistical learning theory has mainly been developed in three directions: the computation of dichotomies with binary-valued functions, the computation of dichotomies with real-valued functions, and the computation of polytomies with functions taking their values in finite sets, typically the set of… (More)

Topics

1 Figure or Table

Cite this paper

@article{Guermeur2007VCTO, title={VC Theory of Large Margin Multi-Category Classifiers}, author={Yann Guermeur}, journal={Journal of Machine Learning Research}, year={2007}, volume={8}, pages={2551-2594} }