Share Email Print

Proceedings Paper

Design rules of multilayer perceptrons
Author(s): Youngjik I. Lee; San-Hoon Oh; Hyun Kyung Song; Myung Won Kim
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Multilayer perceptrons with the error back-propagation learning algorithm are widely used for many pattern classification applications. In this paper, we address some design rules of a multilayer perceptron related to its learning speed and selection of an optimal number of hidden nodes. One of the critical drawbacks of the error back-propagation learning algorithm is its slow learning speed. We have analyzed the reasons for this drawback, and suggested that fast learning can be achieved with proper initial weight settings. Another important problem for multilayer networks is to determine an optimal number of hidden nodes. By analyzing the total error of a multilayer perceptron, we propose an efficient method which yields to an appropriate number of hidden nodes by iteratively eliminating unnecessary hidden nodes. These design rules have been successfully applied to the handwritten digit recognition problem.

Paper Details

Date Published: 1 July 1992
PDF: 11 pages
Proc. SPIE 1710, Science of Artificial Neural Networks, (1 July 1992); doi: 10.1117/12.140099
Show Author Affiliations
Youngjik I. Lee, ETRI (South Korea)
San-Hoon Oh, ETRI (South Korea)
Hyun Kyung Song, ETRI (South Korea)
Myung Won Kim, ETRI (South Korea)

Published in SPIE Proceedings Vol. 1710:
Science of Artificial Neural Networks
Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top