Training artificial neural networks using Taguchi methods

Chris Macleod, Geva Dror, Grant Maxwell

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)

Abstract

This paper shows how the process optimization methods known as Taguchi methods may be applied to the training of Artificial Neural Networks. A comparison is made between the efficiency of training using Taguchi methods and the efficiency of conventional training methods; attention is drawn to the advantages of Taguchi methods. Further, it is shown that Taguchi methods offer potential benefits in evaluating network behaviour such as the ability to examine interaction of weights and neurons within a network.
Original languageEnglish
Pages (from-to)177-184
Number of pages8
JournalArtificial Intelligence Review
Volume13
Issue number3
DOIs
Publication statusPublished - 30 Jun 1999

Keywords

  • Taguchi methods
  • network training
  • network learning
  • statistical methods

Fingerprint Dive into the research topics of 'Training artificial neural networks using Taguchi methods'. Together they form a unique fingerprint.

Cite this