Title: Dynamic behaviour study of Delayed Discrete Hopfield Neural Networks

Authors: Run-Nian Ma, Hua-Feng Guan, Guo-Qiang Bai, Sheng-Rui Zhang

Addresses: Telecommunication Engineering Institute, Air Force Engineering University, Xi'an 710077, China. ' Telecommunication Engineering Institute, Air Force Engineering University, Xi'an 710077, China. ' Institute of Microelectronics, Tsinghua University, Beijing 100084, China. ' School of Highway, Chang'an University, Xi'an 710064, China

Abstract: The stability of Discrete Hopfield Neural Networks (DHNNs) with delay is mainly studied by using energy function and taking some inequality techniques into account. Some results on the stability of the delayed networks are given in this paper. The condition for the delayed networks having no stable state is obtained. Some sufficient conditions for the delayed networks converging towards a limit cycle with 4-period are presented. Also, one criterion is established, which ensures the delayed network having neither a stable state nor a limit cycle with 2-period. The results presented here are also discussed from the point of view of its relationship to some previous results on the stability of the DHNN with delay and without delay.

Keywords: discrete neural networks; delayed networks; stability; limit cycle; Hopfield neural networks; delayed HNNs; DHNNs.

DOI: 10.1504/IJSCC.2010.035424

International Journal of Systems, Control and Communications, 2010 Vol.2 No.4, pp.431 - 445

Published online: 30 Sep 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article