Using a neural network and genetic algorithm to extract decision rules

Karen Blackmore, Terence Bossomaier

Research output: Book chapter/Published conference paperConference paper

13 Downloads (Pure)

Abstract

Rule extraction from neural networks often focusses on exact equivalence and is often tested on relatively small canonical examples. We apply genetic algorithms to the extract approximate rules from neural networks. The method is robust and works with large networks. We compare the results with rules obtained using state of the art decision tree methods and achieve superior performance to straight forward application of the WEKA implementation of the C5 algorithm, J48.PART
Original languageEnglish
Title of host publicationCombined proceedings of DICTA 2003 and ANZIIS 2003
EditorsBrian C Lovell, Duncan A Campbell, Clinton B Fookes, Anthony J Maeder
Place of PublicationBrisbane
PublisherQueensland University of Technology
Pages187-191
Number of pages5
ISBN (Electronic)1741070392
Publication statusPublished - 2003
EventAustralian and New Zealand Intelligent Information Systems Conference - Sydney, Australia, Australia
Duration: 10 Dec 200312 Dec 2003

Conference

ConferenceAustralian and New Zealand Intelligent Information Systems Conference
CountryAustralia
Period10/12/0312/12/03

Fingerprint Dive into the research topics of 'Using a neural network and genetic algorithm to extract decision rules'. Together they form a unique fingerprint.

  • Cite this

    Blackmore, K., & Bossomaier, T. (2003). Using a neural network and genetic algorithm to extract decision rules. In B. C. Lovell, D. A. Campbell, C. B. Fookes, & A. J. Maeder (Eds.), Combined proceedings of DICTA 2003 and ANZIIS 2003 (pp. 187-191). Queensland University of Technology.