Share Email Print

Proceedings Paper

Fuzzy neural network with fast backpropagation learning
Author(s): Zhiling Wang; Marco De Sario; Andrea Guerriero; Raffaele Mugnuolo
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Neural filters with multilayer backpropagation network have been proved to be able to define mostly all linear or non-linear filters. Because of the slowness of the networks' convergency, however, the applicable fields have been limited. In this paper, fuzzy logic is introduced to adjust learning rate and momentum parameter depending upon output errors and training times. This makes the convergency of the network greatly improved. Test curves are shown to prove the fast filters' performance.

Paper Details

Date Published: 28 March 1995
PDF: 11 pages
Proc. SPIE 2424, Nonlinear Image Processing VI, (28 March 1995); doi: 10.1117/12.205255
Show Author Affiliations
Zhiling Wang, Alenia Spazio SpA and Italian Space Agency (Italy)
Marco De Sario, Univ. of Bari (Italy)
Andrea Guerriero, Univ. of Bari (Italy)
Raffaele Mugnuolo, Italian Space Agency (Italy)

Published in SPIE Proceedings Vol. 2424:
Nonlinear Image Processing VI
Edward R. Dougherty; Jaakko T. Astola; Harold G. Longbotham; Nasser M. Nasrabadi; Aggelos K. Katsaggelos, Editor(s)

© SPIE. Terms of Use
Back to Top