Share Email Print

Proceedings Paper

Determination of optimal RBF network structure by canonical subspace analysis
Author(s): Titus K. Y. Lo; John Litva; Henry Leung
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

An important consideration in designing an RBF network is the choice of the number of hidden units required for the network to generalize optimally. A new method, which is called canonical subspace analysis, is proposed for the selection of the number of hidden units. The numerical results show that with the number of the hidden units determined using the proposed method, minimum prediction errors are obtained.

Paper Details

Date Published: 19 August 1993
PDF: 10 pages
Proc. SPIE 1966, Science of Artificial Neural Networks II, (19 August 1993); doi: 10.1117/12.152633
Show Author Affiliations
Titus K. Y. Lo, McMaster Univ. (Canada)
John Litva, McMaster Univ. (Canada)
Henry Leung, Defence Research Establishment Ottawa (Canada)

Published in SPIE Proceedings Vol. 1966:
Science of Artificial Neural Networks II
Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top