DocumentCode
2293310
Title
State automata extraction from recurrent neural nets using k-means and fuzzy clustering
Author
Cechin, Adelmo Luis ; Regina, Denise ; Simon, Pechmann ; Stertz, Klaus
Author_Institution
UNISINOS Univ., Sao Leopoldo, Brazil
fYear
2003
fDate
6-7 Nov. 2003
Firstpage
73
Lastpage
78
Abstract
This paper presents the use of a recurrent neural network to learn the dynamical behavior of the inverted pendulum and from this network to extract a finite state automata. Two clustering methods are compared for the automata extraction: the K-means method, and the construction of fuzzy membership functions. It is shown that the number of states for the fuzzy clustering method induces much less states than the K-means method.
Keywords
finite automata; fuzzy logic; fuzzy systems; nonlinear systems; pendulums; recurrent neural nets; finite state automata; fuzzy clustering; fuzzy membership functions; k-means clustering; recurrent neural nets; state automata extraction; Automatic control; Clustering methods; Control systems; Fuzzy neural networks; Learning automata; Neural networks; Nonlinear control systems; Nonlinear dynamical systems; Recurrent neural networks; State-space methods;
fLanguage
English
Publisher
ieee
Conference_Titel
Chilean Computer Science Society, 2003. SCCC 2003. Proceedings. 23rd International Conference of the
ISSN
1522-4902
Print_ISBN
0-7695-2008-1
Type
conf
DOI
10.1109/SCCC.2003.1245447
Filename
1245447
Link To Document