Fuzzy logic neural networks: Design and computations

The authors introduce and study the architecture of logic-based nets, which use two computational nodes realizing AND and OR logic operations. The resulting three-layer multi-input single output layer called the logic processor makes it possible to realize or approximate any scalar multivalued logic function. The variety of nonlinear characteristics computed for diverse norms made the logical concepts of the network attractive in studies on sensitivity (fault tolerance) and generalization capabilities. The three-layer structure is studied in problems of approximation of many-input one-output nonlinear functions. Learning schemes are developed and analyzed. A collection of logic processors can be used in knowledge acquisition schemes leading to a series of rules induced from empirical data sets.