Globally Exponential Stability and Dissipativity Analysis of Static Neural Networks with Time Delay

Authors: Lijiang Xiang, Shouming Zhong, Yucai Ding

Abstract:

The problems of globally exponential stability and dissipativity analysis for static neural networks (NNs) with time delay is investigated in this paper. Some delay-dependent stability criteria are established for static NNs with time delay using the delay partitioning technique. In terms of this criteria, the delay-dependent sufficient condition is given to guarantee the dissipativity of static NNs with time delay. All the given results in this paper are not only dependent upon the time delay but also upon the number of delay partitions. Two numerical examples are used to show the effectiveness of the proposed methods.

Keywords: Globally exponential stability, Dissipativity, Static neural networks, Time delay.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1335950

References:

[1] C. M. Marcus, R. M. Westervelt, Stability of analog neural networks with delay, Phys. Rev. A, 1989, 39(1), pp. 347-359.
[2] Q. Liu, J. Cao, Y. Xia, A delayed neural network for solving linear projection equations and its analysis, IEEE Trans. Neural Netw., 2005, 16(4), pp. 834-843.
[3] J. Y. Tian, J. Q. Liu, Apnea detection based on time delay neural network, IEEE Engineering in Medicine and Biology 27th Annual Conf., Shanghai, China, 2005, pp. 2571-2574.
[4] J. G. Juang, H. H. Chang, Application of time delay neural network to automatic landing control, IEEE Int. Conf. on Control Applications., 2002, pp. 151-155.
[5] F. Lavagetto, Time-delay neural network for estimating lip movements from speech analysis: a useful tool in audio-video synchronization, IEEE Trans. Circuits Syst. Video Technol., 1997, 7(5), pp. 786-800.
[6] W. L. Ran, J. F. Qiao, X.D. Ye, Soft-measuring approach to on-line predict BOD based on PCA time-delay neural network, Fifth World Congress on Intelligent Control and Automation, Hangzhou, China, 2004, pp. 3483-3487.
[7] S. Arik, Global asymptotic stability of a large class of neural networks with constant time delays, Phys. Lett. A, 2003, 311(6), pp. 504-511.
[8] J. Cao, Periodic oscillation and exponential stability of delayed CNNs, Phys. Lett. A, 2000, 270(3-4), pp. 157-163.
[9] J. Cao, D. Zhou, Stability analysis of delayed cellular neural networks, Neural Netw., 1998, 11(9), pp. 1601-1605.
[10] W. H. Chen, Z. H. Guan, X. Lu, Delay-dependent exponential stability of neural networks with variable delays, Phys. Lett. A, 2004, 326(5-6), pp. 355-363.
[11] W. H. Chen, X. Lu, New delay-dependent exponential stability criteria for neural networks with variable delays, Phys. Lett. A, 2006, 351(1-2), pp. 53-58.
[12] K. Gopalsamy, X. Z. He, Delay independent stability in bidirectional associative memory neural networks, IEEE Trans. Neural Netw., 1994, 5(6), pp. 998-1002.
[13] H. D. Qi, L. Qi, Deriving sufficient conditions for global asymptotic stability of delayed neural networks via nonsmooth analysis, IEEE Trans. Neural Netw., 2004, 15(1), pp. 99-109.
[14] H. Ye, N. Micheal, K. Wang, Robust stability of nonlinear time-delay systems with applications to neural networks, IEEE Trans. Circuits Syst. I, Fundam. Theory Appl., 1996, 43(7), pp. 532-543.
[15] Q. Zhang, X. Wei, J. Xu, Global exponential convergence analysis of delayed neural networks with time varying delays, Phys. Lett. A, 2003, 318(6), pp. 537-544.
[16] H. Qiao, J. Peng, Z. B. Zu, and B. Zhang, A reference model approach to stability analysis of neural network, IEEE Trans. Syst., Man, Cybern. B, Cybern., 2003, 33(6), pp. 925-936.
[17] Z. B. Xu, H. Qiao, and J. Peng, A comparative study on two modeling approaches in neural networks, Neural Netw., 2004, 17(1), pp. 73-85.
[18] Z. Xu, H. Qiao, J. Peng, and B. Zhang, A comparative study of two modeling approaches in neural networks, Neural Netw., 2004, 17(1), pp. 73-85.
[19] S. Xu, J. Lam, D. W. C. Ho, and Y. Zou, Global robust exponential stability analysis for interval recurrent neural networks, Phys. Lett. A, 2004, 325(2), pp. 124-133.
[20] S. Hu and J. Wang, Global stability of a class of continuous-time recurrent neural networks, IEEE Trans. Circuits Syst. I, Fundam. Theory Appl., 2002, 49(9), pp. 1334-1347.
[21] J. Liang and J. Cao, A based-on LMI stability criterion for delayed recurrent neural networks, Chaos Solitons Fract., 2006, 28(1), pp. 154-160.
[22] P. Li and J. Cao, Stability in static delayed neural networks: A nonlinear measure approach, Neurocomputing, 2006, 69(13-15), pp. 1776-1781.
[23] H. Shao, Delay-dependent stability for recurrent neural networks with time-varying delays, IEEE Trans. Neural Netw., 2008, 19(9), pp. 1647-1651.
[24] H. Shao, Novel delay-dependent stability results for neural networks with time-varying delays, Circuits Syst. Signal Process., 2010, 29(4), pp. 637-647.
[25] Z. Zuo, C. Yang, and Y. Wang, A new method for stability analysis of recurrent neural networks with interval time-varying delay, IEEE Trans. Neural Netw., 2010, 21(2), pp. 339-344.
[26] B. Du and J. Lam, Stability analysis of static recurrent neural networks using delay-partitioning and projection, Neural Netw., 2009, 22(4), pp. 343-347.
[27] C. Y. Lu, T. J. Su, and S. C. Huang, Delay-dependent stability analysis for recurrent neural networks with time-varying delay, IET Control Theory Appl., 2008, 2(8), pp. 736-742.
[28] C. D. Zhang, H. Zhang, and Z. Wang, Delay-dependent globally exponential stability criteria for static neural networks: An LMI approach, IEEE Trans. Circuits Syst. II, Exp. Briefs, 2009, 56(7), pp. 605-609.
[29] M. Morita, Associative memory with nonmonotone dynamics, Neural Netw., 1993, 6(1), pp. 115-126.
[30] Y. Liu, Z. Wang, and X. Liu, Global exponential stability of generalized recurrent neural networks with discrete and distributed delays, Neural Netw., 2006, 19(5), pp. 667-675.
[31] Y. Liu, Z. Wang, and X. Liu, On global exponential stability of generalized stochastic neural networks with mixed time-delays, Neurocomputing, 2006, 70(1-3), pp. 314-326, Dec. 2006.
[32] Z. Wang, H. Shu, Y. Liu, D. W. C. Ho, and X. Liu, Robust stability analysis of generalized neural networks with discrete and distributed time delays, Chaos Solitons Fract., 2006, 30(4), pp. 886-896.
[33] Y. Zhao, H. Gao, J. Lam, and K. Chen, Stability analysis of discretetime recurrent neural networks with stochastic delay, IEEE Trans. Neural Netw., 2009, 20(8), pp. 1330-1339.
[34] Y. Liu, Z. Wang, and X. Liu, Asymptotic stability for neural networks with mixed time-delays: The discrete-time case, Neural Netw., 2009, 22(1), pp. 67-74.
[35] H. Wu, W. Zhang, W. Feng, and J. Peng, Delay-dependent stability for static recurrent neural networks via a piecewise delay approach, in Proc. 8th IEEE Int. Conf. Cognitive Informat., 2009, pp. 492-495.
[36] B. Brogliato, R. Lozano, B. Maschke, and O. Egeland, Dissipative Systems Analysis and Control: Theory and Applications. London, U.K.: Springer-Verlag, 2007.
[37] H. Zhang, Z. Guan, and G. Feng, Reliable dissipative control for stochastic impulsive systems, Automatica, 2008, 44(4), pp. 1004-1010.
[38] Z. Feng, J. Lam, and H. Gao, α-dissipativity analysis of singular timedelay systems, Automatica, 2011, 47(11), pp. 2548-2552.
[39] Z. Feng and J. Lam, Stability and dissipativity analysis of distributed delay cellular neural networks, IEEE Trans. Neural Netw., 2011, 22(6), pp. 976-981.
[40] Z. G. Wu. J. Lam, Stability and dissipativity analysis of static neural networks with time dealy, IEEE Trans. Neural Netw., 2012, 23(2), pp. 199-210.
[41] C. D. Zheng, H. Zhang, and Z. Wang, Novel delay-dependent criteria for global robust exponential stability of delayed cellular neural networks with norm-bounded uncertainties, Neurocomputing, 2009, 72(7-9), pp. 1744-1754.
[42] Q. Zhang, X. Wei, and J. Xu, Delay-dependent exponential stability of cellular neural networks with time-varying delays, Chaos, Solitons Fractals, 2005, 23(4), pp. 1363-1369.
[43] Z. Shu and J. Lam, Exponential estimates and stabilization of uncertain singular systems with discrete and distributed delays, Int. J. Control, 2008, 81(6), pp. 865-882.
[44] K. Gu, V. K. Kharitonov, and J. Chen, Stability of Time-Delay Systems. Boston, MA: Birkhauser, 2003.
[45] P. Park, J. W. Ko, and C. Jeong, Reciprocally convex approach to stability of systems with time-varying delays, Automatica, 2011, 47(1), pp. 235-238.
[46] S. Boyd, L. E. I. Ghaoui, E. Feron, and V. Balakrishnan, Linear Matrix Inequality in System and Control Theory. Philadelphia, PA: SIAM, 1994.
[47] C. D. Zheng, H. Zhang, and Z. Wang, New delay-dependent global exponential stability criterion for cellular type neural networks with timevarying delays, IEEE Trans. Circuits Syst. II, Exp. Briefs, 2009, 56(3), pp. 250-254.