Abstract
The paper presents M-matrix algebraic criteria for the input-to-state stability of a class of stochastic recurrent neural networks with Markovian switching. First, the criterion without the time delays is derived. Then, the result is extended to time-varying condition. The criterion also ensures globally exponential stability if there is no input term. These conditions are the improvement and extension of the existing results in the literature. A numerical example is given to demonstrate the effectiveness of the proposed algebraic criteria.
Similar content being viewed by others
References
Chua LO, Yang L (1988) Cellular neural networks: theory. IEEE Trans Circuits Syst 35(10):1257–1272
Cohen MA, Grossberg S (1983) Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Trans Syst Man Cybern 13(5):815–821
Arik S (2002) An analysis of global asymptotic stability of delayed cellular neural networks. IEEE Trans Neural Netw 13(5):1239–1242
Cao J, Yuan K, Li H (2006) Global asymptotical stability of recurrent neural networks with multiple discrete delays and distributed delays. IEEE Trans Neural Netw 17(6):1646–1651
He Y, Wu M, She J (2006) Delay-dependent exponential stability for delayed neural networks with time-varying delay. IEEE Trans Circuits Syst II Express Briefs 53(7):553–557
Chen W, Lu X (2008) Mean square exponential stability of uncertain stochastic delayed neural networks. Phys Lett A 372(7):1061–1069
Raja UK, Raja R, Samidurai R, Leelamani A (2014) Exponential stability for stochastic delayed recurrent neural networks with mixed time-varying delays and impulses: the continuous-time case. Phys Scr 87(5):055802
Raja R, Anthoni SM (2012) New delay dependent robust asymptotic stability for uncertain stochastic recurrent neural networks with discrete and distributed time varying delays. J Frankl Inst 349:2108–2123
Raja R, Sakthivel R, Anthoni SM (2011) Delay-dependent stability criteria of stochastic uncertain Hopfield neural networks with unbounded distributed delays and impulses. Adv Syst Sci Appl 10(1):94–110
Raja R, Sakthivel R, Anthoni SM, Kim H (2011) Stability of impulsive Hopfield neural networks with Markovian switching and time-varying delays. Int J Appl Math Comput Sci 21:127–135
Sakthivel R, Raja R, Anthoni SM (2011) Exponential stability for delayed stochastic BAM neural networks with Markovian jumping and impulses. J Optim Theory Appl 150:166–187
Zeng Z, Wang J, Liao X (2003) Global exponential stability of a general class of recurrent neural networks with time-varying delays. IEEE Trans Circuits Syst I Fundam Theory Appl 50(10):1353–1358
Shen Y, Wang J (2008) An improved algebraic criterion for global exponential stability of recurrent neural networks with time-varying delays. IEEE Trans Neural Netw 19(3):528–531
Song Q (2008) Exponential stability of recurrent neural networks with both time varying delays and general activation functions via LMI approach. Neurocomputing 71(13–15):2823–2830
Liang J, Wang Z, Liu X (2009) State estimation for coupled uncertain stochastic networks with missing measurements and time-varying times: the discrete-time case. IEEE Trans Neural Netw 20(5):781–793
Chen T, Rong L (2004) Robust global exponential stability of Cohen-Grossberg neural networks with time delays. IEEE Trans Neural Netw 15(1):203–206
Xu S, Lam J, Ho DWC, Zou Y (2004) Global robust exponential stability analysis for interval recurrent neural networks. Phys Lett A 352(2):124–133
Liberzon D (2003) Switching in systems and control. Birkhauser, Boston
Huang H, Qu Y, Li H (2005) Robust stability analysis of switched Hopfield neural networks with time-varying delay under uncertainty. Phys Lett A 345:345–354
Shen Y, Wang J (2009) Almost sure exponential stability of recurrent neural networks with Markovian switching. IEEE Trans Neural Netw 20(5):840–855
Yuan K, Cao J, Li H (2006) Robust stability of switched Cohen-Grossberg neural networks with mixed time-varying delays. IEEE Trans Syst Man Cybern 36(6):1356–1363
Wang Z, Liu Y, Liu X (2009) State estimation for jumping recurrent neural networks with discrete and distributed delays. Neural Netw 22(1):41–48
Zhu S, Shen Y, Chen G (2010) Exponential passivity of neural networks with time-varying delay and uncertainty. Phys Lett A 375:136–142
Zhu S, Shen Y (2011) Passivity analysis of stochastic delayed neural networks with Markovian switching. Neurocomputing 74:1754–1761
Jiang F, Shen Y, Liu L (2011) Taylor approximation of the solutions of stochastic differential delay equations with Poisson jump. Commun Nonlinear Sci Numer Simul 16(2):798–804
Jiang F, Shen Y, Hu J (2011) Stability of the split-step backward Euler scheme for stochastic delay integro-differential equations with Markovian switching. Commun Nonlinear Sci Numer Simul 16(2):814–821
Sontag ED (1989) Smooth stabilization implies corpime factorization. IEEE Trans Autom Control 34:435–443
Sontag ED (2006) Input to state stability: basic concepts and results. In: Nistri N, Stefani G (eds) Nonlinear optimal control theory, pp 163–220
Sontag ED, Wang Y (1996) New characterizations of input to state stability. IEEE Trans Autom Control 41:1283–1294
Jiang Z, Wang Y (2001) Input-to-state stability for discrete-time nonlinear systems. Automatica 37:857–869
Cao C, Teel AR (2009) Characterizations of input-to-state stability for hybrid systems. Syst Control Lett 58:47–53
Huang L, Mao X (2009) On input-to-state stability of stochastic retarded systems with Markovian switching. IEEE Trans Autom Control 54(8):1898–1902
Fridman E, Dambrine M, Yeganefar N (2008) On input-to-state stability of systems with time-delay: a matrix inequalities approach. Automatica 44:2364–2369
Sontag ED (1995) On the input to state stability property. Eur J Control 1:1–24
Sanchez EN, Perez JP (1999) Input-to-state stability(ISS) analysis for dynamic neural networks. IEEE Trans Circuits Syst I Fundam Theory Appl 46(11):1395–1398
Guo Y (2008) New results on input-to-state convergence for recurrent neural networks with variable inputs. Nonlinear Anal RWA 9:1558–1566
Yu W, Li X (2001) Some stability properties of dynamic neural networks. IEEE Trans Circuits Syst I Fundam Theory Appl 48(2):256–259
Ahn CK (2010) Passive learning and input-to-state stability of switched Hopfield neural networks with time-delay. Inf Sci 180:4582–4594
Mao X, Yuan C (2006) Stochastic differential equations with Markovian switching. Imperial College Press, London
Acknowledgments
This work was supported by the National Science Foundation of China with Grant Nos. 11101434, 61203055 and the Fundamental Research Funds for the Central Universities 2012QNA48.
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Xu, Y., Luo, W., Zhong, K. et al. Mean square input-to-state stability of a general class of stochastic recurrent neural networks with Markovian switching. Neural Comput & Applic 25, 1657–1663 (2014). https://doi.org/10.1007/s00521-014-1649-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-014-1649-2