The present paper is concerned with the mean-square exponential stability for a class of Markovian jumping neural networks with time-varying discrete and distributed delays. The discrete delay is assumed to be time-varying and belong to a given interval, where the lower and upper bounds of delay are available. Based on the newly constructed Lyapunov—Krasovskii functional, some new delay-interval-dependent exponential stability criteria are obtained in terms of linear matrix inequalities. Finally, two numerical examples are given to show the effectiveness of the proposed results.
CichokiA.UnbehauenR., Neural networks for optimization and signal processing (WileyChichester, UK1993).
2.
HaykinS., Neural networks: A comprehensive foundation (Prentice HallEnglewood Cliffs, New Jersey, USA1998).
3.
WangZ.LiuY.LiuX., ‘On global asymptotic stability of neural networks with discrete and distributed delays.’Phys. Lett. A345 (4–6) (2005): 299–308.
4.
ParkJ. H., ‘Further result on asymptotic stability criterion of cellular neural networks with time-varying discrete and distributed delays.’Appl. Math. Comput.182 (2) (2006): 1661–1666.
5.
HeY.LiuG.ReesD.WuM., ‘Stability analysis for neural networks with time-varying interval delay.’IEEE Trans. Neural Network.18 (6) (2007):1850–1854.
6.
LiH.ChenB.ZhouQ.FangS., ‘Robust exponential stability for uncertain stochastic neural networks with discrete and distributed time-varying delays.’Phys. Lett. A372 (19) (2008): 3385–3394.
7.
LiH.ChenB.ZhouQ.QianW., ‘Robust stability for uncertain delayed fuzzy Hopfield neural networks with Markovian jumping parameters.’IEEE Trans. Syst. Man Cybern. B Cybern.39 (1) (2009): 94–102.
8.
WangG.ChenW.LiuY., ‘Delay-dependent global robust stability criterion for neural networks with neutral-type time-varying delays.’Proc. IMechE, Part I: J. Systems and Control Engineering224 (4) (2010): 321–327 DOI: 10.1243/09596518JSCE996.
9.
LiT.LuoQ.SunC. Y.ZhangB. Y., ‘Exponential stability of recurrent neural networks with time-varying discrete and distributed delays.’Nonlinear Anal. R. World Applic.10 (4) (2009): 2581–2589.
10.
ZhuX. L.WangY. Y., ‘Delay-dependent exponential stability for neural networks with discrete and distributed time-varying delays.’Phys. Lett. A373 (44) (2009): 4066–4072.
11.
MaK. Y.YuL.ZhangW. A., ‘Global exponential stability of cellular neural networks with time-varying discrete and distributed delays.’Neurocomputing72 (10–12) (2009): 2705–2709.
12.
LiH.ChenB.ZhouQ.LinC., ‘Robust exponential stability for delayed uncertain Hopfield neural networks with Markovian jumping parameters.’Phys. Lett. A372 (30) (2008): 4996–5003.
13.
LiuH. Y.ZhaoL.ZhangZ. X.OuY., ‘Stochastic stability of Markovian jumping Hopfield neural networks with constant and distributed delays.’Neurocomputing72 (16–18) (2009): 3669–3674.
14.
WangG. J.CaoJ. D.LiangJ. L., ‘Exponential stability in the mean square for stochastic neural networks with mixed time-delays and Markovian jumping parameters.’Nonlinear Dyn.57 (1–2) (2009): 209–218.
15.
GuK.KharitonovV.ChenJ., Stability of time-delay systems (SpringerBerlin2003).
16.
HanQ. L., ‘A discrete delay decomposition approach to stability of linear retarded and neutral systems.’Automatica45 (2) (2009): 517–524.
