Fuzzy set theory and neural network approaches are two technologies which have proved to be useful in the development of intelligent control systems. The central focus of this research is to investigate the linking of these two methodologies for the analysis and construction of intelligent systems. Particular benefit will come on one hand from the use of fuzzy logic structures to help in the crafting of these systems while on the other hand the use of neural concepts will help in the learning and parallel implementation. The work in this project will focus on four areas. This first area is fuzzy logic controllers. Part of the work here will concentrate on improving the performance of these kinds of systems by (among other methods) the development of a neural implementation of fuzzy logic control. This will involve alternative procedures for defuzzification as well as the development of a formal mathematical understanding of these control systems. A second focus of the research is new learning system, emphasing a new model called participatory learning. This model emphasizes the role the current belief system plays in the learning process. Another important aspect of this model is an independent critic which monitors the performance of the current belief system. The third part of the research concentrates on the fundamental relationship between fuzzy set and neural network theory. Here, the P.I. will look at the relationship between the neural aggregation process and the basic operations of fuzzy set theory. A major goal is to make some connection between the set based operations of fuzzy set theory and the vector algebra approach of neural networks. The final part of the research looks at the implementation of fuzzy expert systems rules in a neural framework, to see if these two technologies can provide some insight into the manner in which experts develop rules.