A hybrid method using PSO and NHL algorithms to train Fuzzy Cognitive Maps

In this paper a new hybrid method for training Fuzzy Cognitive Maps is presented. FCMs are based on the knowledge of human experts and may not be accurate enough because of probable mistakes of experts. Thus, some learning methods have been investigated to train FCMs, so that these probable mistakes are covered. Two learning methods, PSO and NHL, and a new hybrid of them are introduced and implemented and tested for a chemical control problem.