×

zbMATH — the first resource for mathematics

Novel delay-dependent stability results for neural networks with time-varying delays. (English) Zbl 1196.93063
Summary: This paper is concerned with the stability of static neural networks with time-varying delays. With the construction of a new Lyapunov functional and advanced techniques for calculating its derivative, a delay-dependent stability criterion is obtained that is less conservative than existing ones. A delay-independent criterion is also given that, together with the delay-dependent one, can be checked using recently developed algorithms. Examples are provided to illustrate the effectiveness and the reduced conservatism of the proposed results.

MSC:
93D05 Lyapunov and other classical stabilities (Lagrange, Poisson, \(L^p, l^p\), etc.) in control theory
92B20 Neural networks for/in biological studies, artificial life and related topics
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] L.B. Almeida, Back propagation in perceptrons with feedback, in Neural Computers, ed. by R. Eckmiller, C. Von der Malsburg (Springer, New York, 1998), pp. 199–208
[2] A. Bouzerdoum, T.R. Pattison, Neural network for quadratic optimization with bound constraints. IEEE Trans. Neural Netw. 4, 293–303 (1993) · doi:10.1109/72.207617
[3] J. Cao, J. Wang, Global asymptotic and robust stability of recurrent neural networks with time delays. IEEE Trans. Circuits Syst. I 52(2), 417–426 (2005) · Zbl 1374.93285 · doi:10.1109/TCSI.2004.841574
[4] J. Cao, J. Wang, Global exponential stability and periodicity of recurrent neural networks with time delays. IEEE Trans. Circuits Syst. I 52(5), 920–931 (2005) · Zbl 1374.34279 · doi:10.1109/TCSI.2005.846211
[5] W. Chen, W. Zeng, Global asymptotic stability of a class of neural networks with distributed delays. IEEE Trans. Circuits Syst. I 53(3), 644–652 (2006) · Zbl 1374.34280 · doi:10.1109/TCSI.2005.859051
[6] H. Cho, J. Park, Novel delay-dependent robust stability criterion of delayed cellular neural networks. Chaos Solitons Fractals 32, 1194–1200 (2007) · Zbl 1127.93352 · doi:10.1016/j.chaos.2005.11.040
[7] L. Chua, L. Yang, Cellular neural networks: applications. IEEE Trans. Circuits Syst. I 35, 1273–1290 (1998)
[8] Y. He, G. Liu, D. Rees, New delay-dependent stability criteria for neural networks with time-varying delay. IEEE Trans. Neural Netw. 18(1), 310–314 (2007) · doi:10.1109/TNN.2006.888373
[9] S. Hu, J. Wang, Global stability of a class of continuous-time recurrent neural networks. IEEE Trans. Circuits Syst. I 49(9), 1334–1347 (2002) · Zbl 1368.34072 · doi:10.1109/TCSI.2002.802360
[10] C.C. Hua, C.N. Long, X.P. Guan, New results on stability analysis of neural networks with time-varying delays. Phys. Lett. A 352, 335–340 (2006) · Zbl 1187.34099 · doi:10.1016/j.physleta.2005.12.005
[11] C. Li, X. Liao, Robust stability and robust periodicity of delayed recurrent neural networks with noise disturbance. IEEE Trans. Circuits Syst. I 53(10), 2265–2273 (2006) · doi:10.1109/TCSI.2006.883159
[12] J. Li, A.N. Michel, W. Porod, Analysis and synthesis of a class of neural networks: linear systems operating on a closed hypercube. IEEE Trans. Circuits Syst. 36, 1406–1422 (1989) · Zbl 0689.94004
[13] T. Li, L. Guo, C. Sun, Robust stability of neural networks with time-varying delays and fractional uncertainties. Neurocomputing 71, 421–427 (2007) · Zbl 05716325 · doi:10.1016/j.neucom.2007.08.012
[14] J. Liang, J. Cao, A based-on LMI stability criterion for delayed recurrent neural networks. Chaos Solitons Fractals 28, 154–160 (2006) · Zbl 1085.68129 · doi:10.1016/j.chaos.2005.04.120
[15] X. Liao, Q. Liu, W. Zhang, Delay-dependent asymptotic stability for neural networks with distributed delays. Nonlinear Anal., Real World Appl. 7, 1178–1192 (2006) · Zbl 1194.34140 · doi:10.1016/j.nonrwa.2005.11.001
[16] S. Mou, H. Gao, W. Qiang, K. Chen, New delay-dependent exponential stability for neural networks with time delays. IEEE Trans. Syst., Man, Cybern. B, Cybern. 38(2), 571–576 (2008) · doi:10.1109/TSMCB.2007.913124
[17] N. Ozcan, S. Arik, Global robust stability analysis of neural networks with multiple time delays. IEEE Trans. Circuits Syst. I 35(1), 166–176 (2006) · Zbl 1193.92004 · doi:10.1109/TCSI.2005.855724
[18] H. Shao, Delay-dependent approaches to globally exponential stability for recurrent neural networks. IEEE Trans. Circuits Syst. II 55(6), 591–595 (2008) · doi:10.1109/TCSII.2007.916727
[19] S. Xu, J. Lam, D.W.C. Ho, Y. Zou, Global robust exponential stability analysis for interval recurrent neural networks. Phys. Lett. A 325, 124–133 (2004) · Zbl 1161.93335 · doi:10.1016/j.physleta.2004.03.038
[20] Z.B. Xu, H. Qiao, J. Peng, B. Zhang, A comparative study on two modeling approaches in neural networks. Neural Netw. 17, 73–85 (2004) · Zbl 1082.68099 · doi:10.1016/S0893-6080(03)00192-8
[21] S. Xu, J. Lam, D. Ho, Y. Zhou, Improved global robust asymptotic stability criteria for delayed cellular neural networks. IEEE Trans. Syst., Man, Cybern. B, Cybern. 35(6), 1317–1321 (2005) · doi:10.1109/TSMCB.2005.851539
[22] S. Xu, J. Lam, D.W.C. Ho, Y. Zhou, Novel global asymptotic stability criteria for delayed cellular neural network. IEEE Trans. Circuits Syst. II 52, 349–353 (2005) · doi:10.1109/TCSII.2005.849000
[23] S. Xu, J. Lam, D.W.C. Ho, A new LMI condition for delayed dependent asymptotic stability of delayed Hopfied neural networks. IEEE Trans. Circuits Syst. II 52(3), 230–234 (2006)
[24] Z. Zeng, J. Wang, X. Liao, Global exponential stability of a general class of recurrent neural networks with time-varying delays. IEEE Trans. Circuits Syst. I 50(10), 1353–1358 (2003) · Zbl 1368.34089 · doi:10.1109/TCSI.2003.817760
[25] B. Zhang, S. Xu, Y. Zou, Improved delay-dependent exponential stability criteria for discrete-time recurrent neural networks with time-varying delays. Neurocomputing 72, 321–330 (2008) · Zbl 05718828 · doi:10.1016/j.neucom.2008.01.006
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.