LOGICAL OPERATION BASED FUZZY MLP FOR CLASSIFICATION AND RULE GENERATION

A fuzzy layered neural network for classification and rule generation is proposed using logical neurons. It can handle uncertainty and/or im preciseness in the input as well as the output. Logical operators, nam ely, t-norm T and t-conorm S involving And and Or neurons, are employe d in place of the weighted sum and sigmoid functions. Various fuzzy im plication operators are introduced to incorporate different amounts of mutual interaction during the back propagation of errors. In case of partial inputs the model is capable of querying the user for the more important feature information, if and when required. Justification for an inferred decision may be produced in rule form. The built-in And-O r structure of the network enables the generation of appropriate rules expressed as the disjunction of conjunctive clauses. The effectivenes s of the model is tested on a speech recognition problem and on some a rtificially generated pattern sets.