INTERDISCIPLINARY PHYSICS AND RELATED AREAS OF SCIENCE AND TECHNOLOGY |
Prev
Next
|
|
|
Chaotic diagonal recurrent neural network |
Wang Xing-Yuan(王兴元) and Zhang Yi(张诣)† |
School of Electronic and Information Engineering, Dalian University of Technology, Dalian 116024, China |
|
|
Abstract We propose a novel neural network based on a diagonal recurrent neural network and chaos, and its structure and learning algorithm are designed. The multilayer feedforward neural network, diagonal recurrent neural network, and chaotic diagonal recurrent neural network are used to approach the cubic symmetry map. The simulation results show that the approximation capability of the chaotic diagonal recurrent neural network is better than the other two neural networks.
|
Received: 06 May 2011
Revised: 08 November 2011
Accepted manuscript online:
|
PACS:
|
87.19.lj
|
(Neuronal network dynamics)
|
|
05.45.Gg
|
(Control of chaos, applications of chaos)
|
|
Fund: Project supported by the National Natural Science Foundation of China (Grant Nos. 61173183, 60973152, and 60573172), the Superior University Doctor Subject Special Scientific Research Foundation of China (Grant No. 20070141014), and the Natural Science Foundation of Liaoning Province, China (Grant No. 20082165). |
Corresponding Authors:
Zhang Yi,zoey0313@sina.com
E-mail: zoey0313@sina.com
|
Cite this article:
Wang Xing-Yuan(王兴元) and Zhang Yi(张诣) Chaotic diagonal recurrent neural network 2012 Chin. Phys. B 21 038703
|
[1] Liu A Q, Shih S C and Wang Q J 2009 IEEE Trans. Syst. Man Cy. A 39 426[2] Xie W F, Zhu Y Q and Wong Y K 2009 Neurocomputing 72 3277[3] He G G, Zhu P, Chen H P and Cao Z T 2006 Acta Phys. Sin. 55 1040 (in Chinese)[4] Lu H T 2002 Phys. Lett. A 298 109[5] Tang Q and Wang X Y 2010 Chin. Phys. Lett. 27 030508[6] Zhang H G and Wang Z S 2007 IEEE Trans. Neural Networ. 18 947[7] Chen S J and Hong Y G 2011 Chin. Phys. B 20 036401[8] Chen P F, Chen Z Q and Wu W J 2011 Chin. Phys. B 20 040509[9] Gao F R, Wang F L and Li M Z 2000 Chem. Eng. Sci. 55 1283[10] Mastorocostas P A and Theocharis J B 2006 IEEE Trans. Syst. Man Cy. B 36 242[11] Cao J C and Lin X C 2008 Eng. Appl. Artif. Intel. 21 1255[12] Mastorocostas P A and Hilas C S 2009 Neural Comput. Appl. 18 707[13] Zhang H G and Luo Y H 2009 IEEE Trans. Neural Networ. 20 1490[14] Dong M, Zhang H G and Wang Y C 2009 Neurocomputing 72 1999[15] Ji X D and Familoni B O 1999 IEEE Trans. Automat. Contr. 44 1469[16] Rogers T D and Whitley D C 1983 Math. Model. 4 9[17] Aienberg I, Paliy D V, Zurada J M and Astola J T 2008 Neural Networ. 19 883[18] Gu Z Q and Oyadiji S O 2008 J. Vib. Acoust. 130 061001 |
No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|