Optimal ν-SVM parameter estimation using multi objective evolutionary algorithms

James Ethridge, Gregory Ditzler, Robi Polikar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations

Abstract

Using a machine learning algorithm for a given application often requires tuning design parameters of the classifier to obtain optimal classification performance without overfitting. In this contribution, we present an evolutionary algorithm based approach for multi-objective optimization of the sensitivity and specificity of a ν-SVM. The ν-SVM is often preferred over the standard C-SVM due to smaller dynamic range of the ν parameter compared to the unlimited dynamic range of the C parameter. Instead of looking for a single optimization result, we look for a set of optimal solutions that lie along the Pareto optimality front. The traditional advantage of using the Pareto optimality is of course the flexibility to choose any of the solutions that lies on the Pareto optimality front. However, we show that simply maximizing sensitivity and specificity over the Pareto front leads to parameters that appear to be mathematically optimal yet still cause overfitting. We propose a multiple objective optimization approach with three objective functions to find additional parameter values that do not cause overfitting.

Original languageEnglish (US)
Title of host publication2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010
DOIs
StatePublished - Dec 1 2010
Externally publishedYes
Event2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010 - Barcelona, Spain
Duration: Jul 18 2010Jul 23 2010

Publication series

Name2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010

Conference

Conference2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010
CountrySpain
CityBarcelona
Period7/18/107/23/10

Keywords

  • evolutionary algorithms
  • multi-objective optimization
  • ν-SVM

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Optimal ν-SVM parameter estimation using multi objective evolutionary algorithms'. Together they form a unique fingerprint.

Cite this