An efficient training method for recurrent fuzzy neural networks is proposed. The method modifies the RPROP algorithm, originally developed for static neural networks, in order to be applied to dynamic systems. A comparative analysis with the standard back propagation through time is given, indicating the effectiveness of the proposed algorithm.
References
-
-
1)
-
Riedmiller, M., Braun, H.: `A direct adaptive method for faster backpropagation learning: the RPROP algorithm', Proc. IEEE Int. Joint Conf. on Neural Networks, 1993, San Francisco, CA, USA, p. 586–591.
-
2)
-
S. Piche
.
Steepest descent algorithms for neural network controllers and filters.
IEEE Trans. Neural Netw.
,
2 ,
198 -
221
-
3)
-
C. Igel ,
M. Husken
.
Empirical evaluation of the improved RPROP learning algorithms.
Neurocomputing
,
50 ,
105 -
123
-
4)
-
C.-F. Juang ,
C.-T. Lin
.
A recurrent self-organizing neural fuzzy inference network.
IEEE Trans. Neural Netw.
,
4 ,
828 -
845
-
5)
-
P. Mastorocostas ,
J. Theocharis
.
A recurrent fuzzy neural model for dynamic system identification.
IEEE Trans. Syst. Man Cybern B, Cybern.
,
2 ,
176 -
190
http://iet.metastore.ingenta.com/content/journals/10.1049/el_20040052
Related content
content/journals/10.1049/el_20040052
pub_keyword,iet_inspecKeyword,pub_concept
6
6