Share Email Print

Proceedings Paper

Reconfigurating feedforward networks with fewer hidden nodes
Author(s): Iwao Sekita; Takio Kurita; David K. Y. Chiu; H. Asoh
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

The number of nodes in a hidden layer of a feedforward layered network reflects an optimality condition of the network in coding a function. It also affects the computation time and the ability of the network to generalize. When an arbitrary number of hidden nodes is used in designing the network, redundancy of hidden nodes often can be seen. In this paper, a method of reducing hidden nodes is proposed on the condition that a reduced network maintains the performances of the original network with accepted level of tolerance. This method can be applied for estimation of performances of a network with fewer hidden nodes. The estimated performances are the lower bound of the actual performances of the network. Experiments were performed on the Fisher's IRIS data, a set of SONAR data, and the XOR data for classification. Their results suggest that sufficient number of hidden nodes, fewer than the original number, can be estimated by the present method.

Paper Details

Date Published: 1 September 1993
PDF: 9 pages
Proc. SPIE 1962, Adaptive and Learning Systems II, (1 September 1993); doi: 10.1117/12.150596
Show Author Affiliations
Iwao Sekita, MITI (Japan)
Takio Kurita, MITI (Japan)
David K. Y. Chiu, Univ. of Guelph (Canada)
H. Asoh, MITI (Japan)

Published in SPIE Proceedings Vol. 1962:
Adaptive and Learning Systems II
Firooz A. Sadjadi, Editor(s)

© SPIE. Terms of Use
Back to Top