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

Pham, DT; SAĞIROĞLU, ŞEREF

doi:10.1016/s0890-6955(00)00073-0

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

Atıf İçin Kopyala

Pham D., SAĞIROĞLU Ş.

INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE, cilt.41, sa.3, ss.419-430, 2001 (SCI-Expanded)

Yayın Türü: Makale / Tam Makale
Cilt numarası: 41 Sayı: 3
Basım Tarihi: 2001
Doi Numarası: 10.1016/s0890-6955(00)00073-0
Dergi Adı: INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE
Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
Sayfa Sayıları: ss.419-430
İstanbul Teknik Üniversitesi Adresli: Hayır

Özet

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.