PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Embedding sample points relevance in SVM linear classification
Bruno Apolloni and Dario Malchiodi
In: MDAI 2006: Modeling Decisions for Artificial Intelligence, 3-5 Apr 2006, Tarragona, Cataluña, Spain.

Abstract

We propose a Support Vector Machine learning algorithm for classifying points that are affected by both a label and a relevance measure. This paper formalizes the algorithm and discusses its charac- teristics numerically through some study cases.

EPrint Type:Conference or Workshop Item (Paper)
Additional Information:Paper published in the CD proceedings of the conference.
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:2281
Deposited By:Dario Malchiodi
Deposited On:22 October 2006