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

被引：58

作者：

Pham, DT

Sagiroglu, S

机构：

[1] Cardiff Univ, Mfg Engn Ctr, Intelligent Syst Lab, Cardiff CF24 3TE, S Glam, Wales

[2] Erciyes Univ, Fac Engn, Dept Comp Engn, Intelligent Syst Res Grp, TR-38039 Kayseri, Turkey

来源：

INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE | 2001年 / 41卷 / 03期

关键词：

multilayered perceptrons; training algorithms; control chart pattern recognition; wood inspection;

D O I：

10.1016/S0890-6955(00)00073-0

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

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.

引用

页码：419 / 430

页数：12

共 27 条

[1] EFFICACY OF MODIFIED BACKPROPAGATION AND OPTIMIZATION METHODS ON A REAL-WORLD MEDICAL PROBLEM [J].