NEURAL NETWORKS IN DESIGNING FUZZY-SYSTEMS FOR REAL-WORLD APPLICATIONS

A special multilayer perceptron architecture known as FuNe I is succes sfully used for generating fuzzy systems for a number of real world ap plications. The FuNe I trained with supervised learning can be used to extract fuzzy rules from a given representative input/output data set . Furthermore, optimization of the knowledge base is possible includin g the tuning of membership functions. The new method employed to ident ify the rule relevant nodes before the rules are extracted makes FuNe I suitable for applications with large number of inputs. Some of the r eal world applications in areas of state identification and image clas sification show encouraging results in a shorter development time. Exp ert knowledge is not compulsory but can be included in the automatical ly extracted knowledge base. The generated fuzzy system can be impleme nted in hardware very easily. A flexible prototype board is developed with a FPGA chip in order to run applications with up to 128 inputs an d 4 outputs in realtime (1.25 million rules per second).