4538
12
2888
3
14585
document
2888
IJMPB174209.pdf
application/pdf
203170
20091208 20:53:13
http://cogprints.org/4538/1/IJMPB174209.pdf
4538
1
application/pdf
application/pdf
en
public
IJMPB174209.pdf

http://eprints.org/relation/hasVolatileVersion
http://cogprints.org/id/document/6299

http://eprints.org/relation/haspreviewThumbnailVersion
http://cogprints.org/id/document/6299

http://eprints.org/relation/hasVersion
http://cogprints.org/id/document/6299

http://eprints.org/relation/hasVolatileVersion
http://cogprints.org/id/document/8514

http://eprints.org/relation/hasVersion
http://cogprints.org/id/document/8514

http://eprints.org/relation/hasIndexCodesVersion
http://cogprints.org/id/document/8514
archive
3813
disk0/00/00/45/38
20050918
20110311 08:56:11
20070912 17:00:40
journalp
show
0
The chaotic neural network constructed with chaotic neurons exhibits very rich dynamic
behaviors and has a nonperiodic associative memory. In the chaotic neural network,
however, it is dicult to distinguish the stored patters from others, because the states of
output of the network are in chaos. In order to apply the nonperiodic associative memory
into information search and pattern identication, etc, it is necessary to control chaos in
this chaotic neural network. In this paper, the phase space constraint method focused on
the chaotic neural network is proposed. By analyzing the orbital of the network in phase
space, we chose a part of states to be disturbed. In this way, the evolutional spaces of
the strange attractors are constrained. The computer simulation proves that the chaos
in the chaotic neural network can be controlled with above method and the network can
converge in one of its stored patterns or their reverses which has the smallest Hamming
distance with the initial state of the network. The work claries the application prospect
of the associative dynamics of the chaotic neural network.

HE
Guoguang
Dr

CAO
Zhitong
Prof.

CHEN
Hongping
Dr.

ZHU
Ping
Dr
pub
2224
42094214
FALSE
International Journal of Modern Physics B
FALSE
1. CAO Zhitong,\The dynamic associative memory of chaotic neural", J. of Zhejiang
University (Natural Science Edition), Supplement: p. 330{335 (in Chinese), 1998.
2. K. Aihara, T. Takabe and M. Toyoda, \chaotic neural networks". Phys Lett 144(6{7),
333{340 (1990).
3. M. Adachi and K. Aihara \Associative dynamics in a chaotic neural network", Neural
Networks 10(1), 83{98 (1997).
4. E. R. Kobori, K. Ikoda and K. Nakayama, \A model of dynamic associative memory",
IEEE International Conference on Neural Networks Conference Proceedings 2, 804{809
(1996).
5. He Guoguang and Cao Zhitong, \Controlling chaos in chaotic neural network", Acta
Physica Sinica 50(11), p. 2103{2107 (in Chinese), 2001.
6. E. Ott, C. Grebogi and J. A. Yorke, \Controlling chaos", Phys. Rev. Lett. 64(11),
p. 1196{1199 (1990).
7. Pyragas, K. \Continuous Control of Chaos by SelfControlling Feedback", Phys. Lett.
A170, p. 421{428 (1992).
8. X. S. Luo, \Using phase space compression to control chaos and hyperchaos", Acta
Physica Sinica, 48(3), p. 402{406 (in Chinese), 1999.
 compscimachdynamsys
Controlling Chaos in a Neural Network Based on the Phase Space Constraint
17
published
200309
public