LEARNING RULES FOR A FUZZY INFERENCE MODEL

The problem of learning rules for a fuzzy inference model directly from empirical observations, without resorting to assessments from experts is considered. We develop a method that builds uncertain rules from a set of examples. These rules match the following pattern: If X is A then Y is B is [alpha, beta],where A and B are fuzzy sets representing fuzzy restrictions on the variables X and Y; alpha and beta are real numbers expressing lower and upper degrees of certainty in the truth of the rule. The method is based on the minimization of a distance measure between the real output associated to a given input and the output predicted by the inference model using a parameterized version of the same rule to be learnt. Our approach is computationally efficient in running time as well as in storage requirements. Moreover, it can be used in both training (batch-processing) and adaptation (iterative-processing) modes of learning.