Fuzzy connectionist expert systems

Hybrid architectures for intelligent systems is a new field of artificial intelligence research concerned with the development of the next generation of intelligent systems. Current research interests in this field focus on integrating the computational paradigm of expert systems with new emergent paradigms such as neural networks, fuzzy logic, and genetic algorithms. The ability to learn in uncertain or unknown environments is an essential component of any intelligent system and is particularly crucial to its performance. This ability, which is lacking in traditional expert systems, can be achieved by incorporating neural network and genetic algorithm learning mechanisms into expert systems. These learning techniques enable expert systems to modify and/or enrich their knowledge structures autonomously. Another usual deficiency in classical expert systems is uncertainty treatment. Fuzzy logic appears as an adequate paradigm to deal with the vagueness, inaccuracy, incompleteness, and inconsistency frequently associated with the human reasoning. Much of the logic behind human reasoning is not the traditional two-valued, or even multivalued logic, but a logic with fuzzy truths, fuzzy connectives and fuzzy rules of inference. In this paper the authors describe an expert system architecture using the above mentioned paradigms, aimed at solving classification problems. Classification appears to be a powerful human strategy for organizing knowledge for comprehension and action, being used in many practical applications, such as identification, selection, diagnosis, debugging, monitoring, forecast, etc. The authors call such hybrid systems fuzzy connectionist expert systems