Application of fuzzy, GA and hybrid methods to CNN template learning

In this paper, a novel methodology is presented for template learning using genetic algorithm (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 other works in template learning with classical GA-approach, the genetic algorithms are used to optimize the fuzzy rule sets, which finally produce an optimal template for the desired task. The final rule base of characteristics of the input, and master images 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.