PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

DISPERSION EFFECT ON GENERALIZATION ERROR IN CLASSIFICATION - Experimental Proof and Practical Algorithm
Benoît Gandar, Gaëlle Loosli and Guillaume Deffuant
ICAART 2011.

Abstract

Recent theoretical work proposes criteria of dispersion to generate learning points. The aim of this paper is to convince the reader, with experimental proofs, that dispersion is a good criterion in practice for generating learning points for classification problems. Problem of generating learning points consists then in generating points with the lowest dispersion. As a consequence, we present low dispersion algorithms existing in the literature, analyze them and propose a new algorithm.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:7181
Deposited By:Gaëlle Loosli
Deposited On:08 March 2011