Design of fuzzy systems using neurofuzzy networks

This paper introduces a systematic approach for fuzzy system design based o n a class of neural fuzzy networks built upon a general neuron model. The n etwork structure is such that it encodes the knowledge learned in the form of if-then fuzzy rules and processes data following fuzzy reasoning princip les, The technique provides a mechanism to obtain rules covering the whole input/output space as well as the membership functions (including their sha pes) for each input variable. Such characteristics are of utmost importance in fuzzy systems design and application. In addition, after learning, it i s very simple to extract fuzzy rules in the linguistic form, The network ha s universal approximation capability, a property very useful in, e.g., mode ling and control applications, Here we focus on function approximation prob lems as a vehicle to illustrate its usefulness and to evaluate its performa nce. Comparisons with alternative approaches are also included. Both, nonno isy and noisy data have been studied and considered in the computational ex periments, The neural fuzzy network developed here and, consequently, the u nderlying approach, has shown to provide good results from the accuracy, co mplexity, and system design points of view.