PETRI-NET MODELS OF FUZZY NEURAL NETWORKS

Artificial neural networks (ANN's) are highly parallel and distributed computational structures that can learn from experience and perform i nferences. Petri nets, on the other hand, provide an effective modelin g framework for distributed systems. The basic concepts of Petri net a re utilized to develop ANN-like multilayered Petri net architectures o f distributed intelligence having learning ability. A Petri net model of single neuron is presented. A two-layer Petri net model-Neural Petr i Net (NPN)-that uses this neuron model as a building block is describ ed. A new class of Petri nets called the Fuzzy Neural Petri Net (FNPN) is defined. The FNPN can be used for representing a fuzzy knowledge b ase and for fuzzy reasoning. Some application examples for the two Pet ri net based models are given.