DocumentCode
1750636
Title
A method to induce fuzzy automata using neural networks
Author
Blanco, Alberto ; Delgado, M. ; Pegalajar, M.C.
Author_Institution
Dept. de Ciencias de la Comput. e Inteligencia Artificial, Granada Univ.
fYear
2001
fDate
25-28 July 2001
Firstpage
3054
Abstract
It has been shown that neural networks are able to infer regular crisp grammars from positive and negative examples. The fuzzy grammatical inference problem however has received considerably less attention. In this paper we show that a suitable two-layer neural network model is able to infer fuzzy regular grammars from a set of fuzzy examples belonging to a fuzzy language. Once the network has been trained, we develop methods to extract a deterministic representation of the fuzzy automaton encoded in the network that recognizes the training set
Keywords
automata theory; formal languages; fuzzy neural nets; grammars; inference mechanisms; multilayer perceptrons; deterministic representation; fuzzy automata; fuzzy grammatical inference problem; regular crisp grammars; two-layer neural network model; Artificial neural networks; Automata; Electronic mail; Fuzzy neural networks; Fuzzy sets; Network topology; Neural networks; Neurons; Recurrent neural networks; Uncertainty;
fLanguage
English
Publisher
ieee
Conference_Titel
IFSA World Congress and 20th NAFIPS International Conference, 2001. Joint 9th
Conference_Location
Vancouver, BC
Print_ISBN
0-7803-7078-3
Type
conf
DOI
10.1109/NAFIPS.2001.943715
Filename
943715
Link To Document