Implementation of conjunctive and disjunctive fuzzy logic rules with neural networks

AbstractThe use of fuzzy logic to model and manage uncertainty in a rule-based system places high computational demands on an inference engine. In an earlier paper, we introduced trainable neural network structures for fuzzy logic. These networks can learn and extrapolate complex relationships between possibility distributions for the antecedents and consequents in the rules. In this paper, the power of these networks is further explored. The sensitivity of the output to noisy input distributions (which are likely if the clauses are generated from real data) is demonstrated as well as the ability of the networks to internalize multiple conjunctive clause and disjunctive clause rules. Since different rules (with the same variables) can be encoded in a single network, this approach to fuzzy logic inference provides a natural mechanism for rule conflict resolution