Simple heuristic approach for training of Type-2 NEO-Fuzzy Neural Network

This paper describes the development of Interval Type-2 NEO-Fuzzy Neural Network for modeling of complex dynamics. The proposed network represents a parallel set of multiple zero order Sugeno type approximations, related only to their own input argument. As learning procedure a simple heuristic backpropagation approach, where the sign of the gradient is taken into account, is adopted. To improve the robustness of the network and the possibilities for handling uncertainties, Interval Type-2 Gaussian fuzzy sets are introduced into the network topology. The potentials of the proposed approach in modeling of Mackey-Glass and Rossler Chaotic time series are studied. A comparison is made with the classical Gradient Descent learning approach.