New PTH Moment Stable Criteria of Stochastic Neural Networks

Authors: Zixin Liu, Huawei Yang, Fangwei Chen

Abstract:

In this paper, the issue of pth moment stability of a class of stochastic neural networks with mixed delays is investigated. By establishing two integro-differential inequalities, some new sufficient conditions ensuring pth moment exponential stability are obtained. Compared with some previous publications, our results generalize some earlier works reported in the literature, and remove some strict constraints of time delays and kernel functions. Two numerical examples are presented to illustrate the validity of the main results.

Keywords: Neural networks, stochastic, PTH moment stable, time varying delays, distributed delays.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1061822

References:

[1] L. Sheng and H.Z. Yang. Exponential synchronization of a class of neural networks with mixed time-varying delays and impulsive effects. Neurocomputing, 7: 3666-3674.
[2] O.M. Kwon and J.H. Park. Exponential stability for uncertain cellular neural networks with discrete and distributed time-varying delays. Appl. Math. Comput, 203: 813-823.
[3] Y.H. Xia, Z.K. Huang and M.A. Han. Exponential p-stability of delayed Cohen-Grossberg-type BAM neural networks with impulses. Chaos, Solitons and Fractals, 38: 806-818.
[4] P. Balasubramaniam and R. Rakkiyappan. Global asymptotic stability of stochastic recurrent neural networks with multiple discrete delays and unbounded distributed delays. Appl. Math. Comput, 204: 680-686.
[5] P. Balasubramaniam and R. Rakkiyappan. LMI conditions for global asymptotic stability results for neutral-type neural networks with distributed time delays. Appl. Math. Comput, 204: 317-324.
[6] J.J. Yu et al. Simplified exponential stability analysis for recurrent neural networks with discrete and distributed time-varying delays. Appl. Math. Comput, 205:465-474.
[7] S. Haykin. Neural Networks. Prentice-Hall, NJ.
[8] C.X. Huang, Y.G. He, P. Chen. Dynamic Analysis of Stochastic Recurrent Neural Networks. Neural. Process. Lett, 27: 267-276.
[9] L. Wan, J.H. Sun. Mean square exponential stability of stochastic delayed Hopfield neural networks. Phys. Lett. A,343, : 306-318.
[10] X.Y. Lou, B.T. Cui. Delay-dependent stochastic stability of delayed Hopfield neural networks with Markovian jump parameters. J. Math. Anal. Appl, 328: 316-326.
[11] L.S. Wang, Z. Zhang and Y.F. Wang. Stochastic exponential stability of the delayed reactionCdiffusion recurrent neural networks with Markovian jumping parameters. Phys. Lett. A, 18: 3201-3209.
[12] Z.D. Wang, Y.R. Liu, L. Yu and X.H. Liu. Exponential stability of delayed recurrent neural networks with Markovian jumping parameters. Phys. Lett. A, 4: 346-352.
[13] E.W. Zhu et al. pth Moment Exponential Stability of Stochastic Cohen- Grossberg Neural Networks With Time-varying Delays. Neural. Process. Lett, 26: 191-200.
[14] J. Randjelovic, S. Jankovic. On the pth moment exponential stability criteria of neutral stochastic functional differential equations. J. Math. Anal. Appl, 326 :266-280.
[15] Y.H. Sun, J.D. Cao. pth moment exponential stability of stochastic recurrent neural networks with time-varying delays, Nonlinear Anal. realword, 8: 1171-1185.
[16] C.X. Huang et al. pth moment stability analysis of stochastic recurrent neural networks with time-varying delays. Inf. Sci, 178: 2194-2203.
[17] S.J. Wu, D. Han and X.Z. Meng. p-Moment stability of stochastic differential equations with jumps. Appl. Math. Comput, 152: 505-519.
[18] S.J. Wu, X.L. Guo and Y. Zhou. p-moment stability of functional differential equations with random impulsive. Comput. Math. Appl, 52: 1683-1694.
[19] H.J. Wu, J.T. Sun. p-Moment stability of stochastic differential equations with impulsive jump and Markovian switching. Automatica, 42: 1753- 1759.
[20] X.R. Mao. Exponential Stability of Stochastic Differential Equations. Marcel Dekker, NewYork.
[21] X.R. Mao. Stochastic Differential Equations and Applications. Horwood Publication, Chichester.