Fuzzy system identification through hybrid genetic algorithms

In this paper, we propose a new Hybrid Genetic Algorithm for fuzzy system learning. The algorithm is based on the Baldwin's Effect with the inclusion of biological principles of learning. Rather than considering mutation as a stochastic event, we take into account results of biological experiences that seem to indicate individual capability of choosing the best mutation. The proposed adaptive model consists of two levels: (a) an evolutionary or global level, which works on the generation of populations at genetic code level; and (b) a learning or local level, which works at the time life of the agents with the individuals reacting to environmental stimulus. The method has been applied in well-known learning problems, with strong supremacy over other hybrid genetic approaches, particularly in terms of expressiveness of the learned fuzzy system.