Fuzzy Grammatical Inference Using Neural Network

Abstract

We have shown a model of fuzzy neural network that is able to infer the relations associated to the transitions of a fuzzy automaton from a fuzzy examples set. Neural network is trainned by a backpropagation of error based in a smooth derivative [Blanco96]. Once network has been trainned the fuzzy relations associated to the transitions of the automaton are found encoded in the weights.