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 trained by a backpropagation of error based in a smooth derivative [1]. Once network has been trained the fuzzy relations associated to the transitions of the automaton are found encoded in the weights.
@article{urn:eudml:doc:39129,
title = {Fuzzy grammatical inference using neural network.},
journal = {Mathware and Soft Computing},
volume = {5},
year = {1998},
pages = {133-140},
zbl = {0958.68517},
language = {en},
url = {http://dml.mathdoc.fr/item/urn:eudml:doc:39129}
}
Blanco, Armando; Delgado, A.; Pegalajar, M. Carmen. Fuzzy grammatical inference using neural network.. Mathware and Soft Computing, Tome 5 (1998) pp. 133-140. http://gdmltest.u-ga.fr/item/urn:eudml:doc:39129/