Intelligent Systems : Unified Approach to Knowledge Representation, Analysis and Implementation Based on Fuzzy Petri Nets

Proceedings of the Fourth Bar-Ilan Symposium on Foundations of Artificial Intelligence

Volume

Proceedings of the Fourth Bar-Ilan Symposium on Foundations of Artificial Intelligence

Contents

The design and implementation of Fuzzy Intelligent systems are studied. These systems operate in conditions of uncertainty, imprecision and ambiguity. Their behavior is described by Fuzzy Algorithms (FA) in the form of Fuzzy production rules. A new approach to design of such Fuzzy systems is suggested. The approach is based on a following: (a) Fuzzy Petri Nets (FPN) as new model and tools for a formal representation and modeling of given Fuzzy systems; (b) isomorphism between two representations of Fuzzy algorithms (in terms of its Fuzzy PN and its Fuzzy Finite Automata) as a base for their Hardware realization. The approach proposed here guaranties a simple and an efficient execution of following main stages of an arbitrary Fuzzy system design : (i) Formal description of corresponding FA rules in the form of Fuzzy PN; (ii) Analysis of FA rules; (iii) Hardware implementation of a given Fuzzy system using different element bases. The stages (ii) and (iii) use a structural analysis (synthesis) FA in terms of a functional decomposition (composition) of a corresponding Fuzzy PN from a set of elementary PN-components. The method of mapping from a given Fuzzy algorithm to its Hardware implementation is developed.