|
|
Multistability of delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions |
Huang Yu-Jiao (黄玉娇), Hu Hai-Gen (胡海根) |
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, China |
|
|
Abstract In this paper, the multistability issue is discussed for delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions. Based on a fixed theorem and stability definition, sufficient criteria are established for the existence and stability of multiple equilibria of complex-valued recurrent neural networks. The number of stable equilibria is larger than that of real-valued recurrent neural networks, which can be used to achieve high-capacity associative memories. One numerical example is provided to show the effectiveness and superiority of the presented results.
|
Received: 12 May 2015
Revised: 27 June 2015
Accepted manuscript online:
|
PACS:
|
07.05.Mh
|
(Neural networks, fuzzy logic, artificial intelligence)
|
|
02.30.Ks
|
(Delay and functional equations)
|
|
Fund: Project supported by the National Natural Science Foundation of China (Grant Nos. 61374094 and 61503338) and the Natural Science Foundation of Zhejiang Province, China (Grant No. LQ15F030005). |
Corresponding Authors:
Huang Yu-Jiao
E-mail: hyj0507@zjut.edu.cn
|
Cite this article:
Huang Yu-Jiao (黄玉娇), Hu Hai-Gen (胡海根) Multistability of delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions 2015 Chin. Phys. B 24 120701
|
[1] |
Kwon O M, Kwon J W and Kim S H 2011 Chin. Phys. B 20 050505
|
[2] |
Zhang H G, Yang F S, Liu X D and Zhang Q L 2013 IEEE Trans. Neural Netw. Learn. Syst. 24 513
|
[3] |
Zhang H G, Wang Z S and Liu D R 2014 IEEE Trans. Neural Netw. Learn. Syst. 25 1229
|
[4] |
Lakshmanan S and Balasubramaniam P 2011 Chin. Phys. B 20 040204
|
[5] |
Lakshmanan S, Park J H, Rihan F A and Rakkiyappan R 2014 Chin. Phys. B 23 070205
|
[6] |
Cheng C Y, Lin K H and Shih C W 2007 Physica D 225 61
|
[7] |
Cao J D, Feng G and Wang Y Y 2008 Physica D 237 1734
|
[8] |
Huang Y J, Zhang H G and Wang Z S 2012 Chin. Phys. B 21 070701
|
[9] |
Zeng Z G, Huang T W and Zheng W X 2010 IEEE Trans. Neural Netw. 21 1371
|
[10] |
Zeng Z G and Zheng W X 2013 IEEE Trans. Neural Netw. Learn. Syst. 24 1749
|
[11] |
Wang L L and Chen T P 2014 Neural Netw. 53 109
|
[12] |
Wang L L and Chen T P 2015 Neurocomputing 152 222
|
[13] |
Zhang H G, Huang Y J, Cai T Y and Wang Z S 2014 Int. J. Mod. Phys. B 28 1450118
|
[14] |
Jankowski S, Lozowski A and Zurada J M 1996 IEEE Trans. Neural Netw. 7 1491
|
[15] |
Lee D L 2006 IEEE Trans. Neural Netw. 17 1341
|
[16] |
Hu J and Wang J 2012 IEEE Trans. Neural Netw. Learn. Syst. 23 853
|
[17] |
Hirose A and Yoshida S 2012 IEEE Trans. Neural Netw. Learning Syst. 23 541
|
[18] |
Zhou B and Song Q 2013 IEEE Trans. Neural Netw. Learning Syst. 24 1227
|
[19] |
Chen X and Song Q 2013 Neurocomputing 121 254
|
[20] |
Huang Y J, Zhang H G and Wang Z S 2014 Appl. Math. Comput. 229 187
|
[21] |
Hirose A 2011 Front. Electr. Electron. Eng. China 6 171
|
[22] |
Lee D 2006 IEEE Trans. Neural Netw. 17 1341
|
[23] |
Forti M 2007 Int. J. Circuit Theory Appl. 35 105
|
[24] |
Bao G and Zeng Z G 2012 Neurocomputing 77 101
|
[25] |
Huang Y J, Zhang H G and Wang Z S 2012 Neurocomputing 91 21
|
[26] |
Duan L and Huang L 2014 Neurocomputing 123 318
|
[27] |
Wen S P, Zeng Z G, Huang T W and Zhang Y D 2014 IEEE Trans. Fuzzy Syst. 22 1704
|
[28] |
Wen S P, Zeng Z G, Huang T W, Meng Q G and Yao W 2015 IEEE Trans. Neural Netw. Learn. Syst. 26 1493
|
[29] |
Wen S P, Yu X H, Zeng Z G and Wang J J 2015 IEEE Trans. Ind. Electron.
|
[30] |
Wen S P, Zeng Z G, Huang T W, Yu X H and Xiao M Q 2015 IEEE Trans. Fuzzy Syst.
|
[31] |
Ahlfors L 1979 Complex Analysis (New York: McGraw-Hill)
|
[32] |
Filippov A 1988 Differential Equations with Discontinuous Righthand Sides. Mathematics and Its Applications (Soviet Series) (Boston MA: Kluwer Academic)
|
[33] |
Yosida K 1978 Functional Analysis (Berlin: Springer-Verlag)
|
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
|
|
|