Adaptive neuro-fuzzy modeling
Maurício Figueiredo, Fernando A. C. Gomide · 2002
A new class of adaptive neural fuzzy networks for fuzzy modeling is introduced in this paper. It learns the essential parameters to model a fuzzy system such as fuzzy rules and membership functions. Fuzzy rules are easily encoded and decoded from its structure. These neural fuzzy networks also rigorously emulate fuzzy reasoning mechanisms. Because of their knowledge representation and computational features we can see the proposed system either as a neural fuzzy network or a fuzzy system. Thus, linguistic models are easily extracted from their structure. Simulation results and comparison analysis show that the proposed network has good performance considering two criteria: accuracy and number of rules derived.