A LEARNING PROCEDURE TO IDENTIFY WEIGHTED RULES BY NEURAL NETWORKS

In many cases the identification of systems by means of fuzzy rules is given by taking these rules from a predetermined set of possible ones . In this case, the correct description of the system is to be given b y a finite set of rules each with an associated weight which assesses its correctness or accuracy. Here we present a method to learn this co nsistence level or weight by a neural network. The design of this neur al network as well as the features of the training models are discusse d. The paper concludes with an example.