For the most recent entries see the Petri Nets Newsletter.

A Novel Method for Template Learning of Cellular Neural Networks.

Doan, M.; Halgamuge, S.K.; Glesner, M.

In: Proc. 4th European Congress on Intelligent Techniques and Software Computing, Aachen, Germany, Sep. 2-5, 1996, Vol. 1, pages 505-509. 1996. ISBN 3-89653-187-5.

Abstract: The template coefficients (weights) of a CNN, which will give a desired performance, can be found by learning Genetic Algorithms (GA). In this paper we present a novel methodology for template learning using GA, and GA based fuzzy systems. At the beginning of the learning procedure, several fuzzy systems composed of fuzzy rule sets are randomly initialized. In opposite to template learning with classical GA-approach, the genetic algorithms are used in GA based fuzzy systems to optimize the fuzzy rule sets, which finally produce an optimal template for the desired task. The final rule base of characteristcs of the inputs, significant for the image output, are then applied to the operations of a proper GA approach to alter the templates coefficients in order to minimize the GA run time effort. Results of several applications are shown.

Do you need a refined search? Try our search engine which allows complex field-based queries.

Back to the Petri Nets Bibliography