Paper Titles
The Development of RRM Conformance Test in TD-LTE Idle_State
p.905
Building Complex Network Similar to Facebook
p.909
Performance Analysis of One AP with 802.11g WLAN Network
p.914
Large Capacity Cache Design Based on Emerging Non-Volatile Memory
p.918
New Delay-Dependent Stability Criteria for Recurrent Neural Networks with Time-Varying Delays
p.922
Extending Linear Temporal Logic with Clocks to Object-Z
p.927
On the Potential of Web Services in Network Management
p.931
The Observer Pattern Research Based on rCOS
p.936
A Cross-Domain Access Control Method for Large Organizations
p.941

New Delay-Dependent Stability Criteria for Recurrent Neural Networks with Time-Varying Delays

Article Preview

Abstract:

This paper is concerned with the problem of delay-dependent asymptotic stability criterion for recurrent neural networks with time-varying delays. A new Lyapunov functional is introduced by considering the information of neuron activation functions adequately. By using the improved delay-partitioning method and reciprocally convex approach, a less conservative stability criterion is obtained in terms of linear matrix inequalities (LMIs). A numerical example is finally given to illustrate the effectiveness of the derived method.

You might also be interested in these eBooks
Applied Science, Materials Science and Information Technologies in Industry View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 513-517)

Pages:

922-926

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.513-517.922

Citation:

Cite this paper

Online since:

February 2014

Authors:

Ze Rong Ren*, Xiang Jun Xie

Keywords:

Delay-Dependent Stability, Linear Matrix Inequality (LMI), Neural Network (NN), Time-Varying Delays

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2014 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

References

[1] J. Cao. Global asymptotic stability of neural networks with transmission delays [J]. International Journal of System Science, 2000 31(10)1313-1316.

DOI: 10.1080/00207720050165807

Google Scholar

[2] Y. He, G. Liu, and D. Rees. New delay-dependent stability criteria for neural networks with time-varying delay [J]. IEEE Transactions on Neural Networks, 2007 18(1) 310-314.

DOI: 10.1109/tnn.2006.888373

Google Scholar

[3] T. Li and X. L. Ye. Improved stability criteria of neural networks with time-varying delays: An augmented LKF approach [J]. Neurocomputing, 2010 73(4-6)1038-1047.

DOI: 10.1016/j.neucom.2009.10.001

Google Scholar

[4] H. Zhang, Z. Liu, G. Huang, and Z. Wang. Novel weighting-delaybased stability criteria for recurrent neural networks with time-varying delay [J]. IEEE Transactions on Neural Networks, 2010 21(1) 91-106.

DOI: 10.1109/tnn.2009.2034742

Google Scholar

[5] S. Xiao and X. Zhang, New globally asymptotic stability criteria for delayed cellular neural networks [J]. IEEE Transactions on Circuits and Systems II, 2009 56 (8) 659-663.

DOI: 10.1109/tcsii.2009.2024244

Google Scholar

[6] X. Zhang and Q. Han, New Lyapunov-Krasovskii functionals for global asymptotic stability of delayed neural networks [J]. IEEE Transactions on Neural Networks, 2009 20(3) 533-539.

DOI: 10.1109/tnn.2009.2014160

Google Scholar

[7] S. Boyd, V. Balakrishnan, E. Feron, and L. El Ghaoui. Linear Matrix Inequalities in Systems and Control[M], SIMA, Philadelphia, Pa, USA, July (1994).

DOI: 10.1137/1.9781611970777

Google Scholar

[8] P.G. Park, J.W. Ko, and C. Jeong. Reciprocally convex approach to stability of systems with time-varying delays [J]. Automatica, 2011 47(1) 235-238.

DOI: 10.1016/j.automatica.2010.10.014

Google Scholar