Share Email Print
cover

Proceedings Paper

Generalized cost-criterion-based learning algorithm for diagonal recurrent neural networks
Author(s): Yongji Wang; Hong Wang
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

A new generalized cost criterion based learning algorithm for diagonal recurrent neural networks is presented, which is with form of recursive prediction error (RPE) and has second convergent order. A guideline for the choice of the optimal learning rate is derived from convergence analysis. The application of this method to dynamic modeling of typical chemical processes shows that the generalized cost criterion RPE (QRPE) has higher modeling precision than BP trained MLP and quadratic cost criterion trained RPE (QRPE).

Paper Details

Date Published: 9 May 2000
PDF: 4 pages
Proc. SPIE 4077, International Conference on Sensors and Control Techniques (ICSC 2000), (9 May 2000); doi: 10.1117/12.385516
Show Author Affiliations
Yongji Wang, Huazhong Univ. of Science and Technology (China)
Hong Wang, Univ. of Manchester Institute of Science and Technology (United Kingdom)


Published in SPIE Proceedings Vol. 4077:
International Conference on Sensors and Control Techniques (ICSC 2000)
Desheng Jiang; Anbo Wang, Editor(s)

© SPIE. Terms of Use
Back to Top