Training multilayered perceptrons for pattern recognition: a comparative study of four training algorithms


Pham D., SAĞIROĞLU Ş.

INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE, vol.41, no.3, pp.419-430, 2001 (Journal Indexed in SCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 41 Issue: 3
  • Publication Date: 2001
  • Doi Number: 10.1016/s0890-6955(00)00073-0
  • Title of Journal : INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE
  • Page Numbers: pp.419-430

Abstract

This paper presents an overview of four algorithms used for training multilayered perceptron (MLP) neural networks and the results of applying those algorithms to teach different MLPs to recognise control chart patterns and classify wood veneer defects. The algorithms studied are Backpropagation (BP), Quick-prop (QP), Delta-Bar-Delta (DBD) and Extended-Delta-Bar-Delta (EDBD). The results show that, overall, BP was the best algorithm for the two applications tested. (C) 2001 Elsevier Science Ltd. All rights reserved.