Adaptive Group Organization Cooperative Evolutionary Algorithm for TSK-type Neural Fuzzy Networks Design

This paper proposes a novel adaptive group organization cooperative evolutionary algorithm (AGOCEA) for TSK-type neural fuzzy networks design. The proposed AGOCEA uses group-based cooperative evolutionary algorithm and selforganizing technique to automatically design neural fuzzy networks. The group-based evolutionary divided populations to several groups and each group can evolve itself. In the proposed self-organizing technique, it can automatically determine the parameters of the neural fuzzy networks, and therefore some critical parameters have no need to be assigned in advance. The simulation results are shown the better performance of the proposed algorithm than the other learning algorithms. Keywords—TSK-type Neural Fuzzy Networks; Evolutionary Algorithm; Group based Symbiotic; Self Organization; System Identification