Lagrange Stability of Memristive Recurrent Neural Networks with Delays
Abstract: In this paper, we study the globally exponential stability in a Lagrange sense for memristive re-current neural networks with time-varying delays. By the results from the theories of nonsmooth analysis, differential inclusions and linear matrix inequalities  , a novel sufficient criterion in the form of linear matrix inequality is given to confirm the Lagrange stability of memristive re-current neural networks. Meanwhile, the estimation of the globally exponentially attractive set is also given.
文章引用: 殷芳霞 , 李小林 (2016) 时滞忆阻神经网络的Lagrange稳定性。 理论数学， 6， 272-277. doi: 10.12677/PM.2016.63041
 Clarke, F.H., Ledyaev, Y.S., Stem, R.J. and Wolenski, R.R. (1998) Nonsmooth Analysis and Control Theory. Springer, New York.
Aubin, J.P. and Cellina, A. (1984) Differential Inclusions. Springer-Verlag, Berlin.
Zhang, G.D., Shen, Y. and Sun, J.W. (2012) Global Exponen-tial Stability of a Class of Memristor-Based Recurrent Neural Networks with Time-Varying Delays. Neurocomputing, 97, 149-154.
Wu, A.L. and Zeng, Z.G. (2012) Exponential Stabilization of Memristive Neural Networks with Time Delays. IEEE Transactions on Neural Networks and Learning Systems, 23, 1919-1929.
Zhang, G.D., Shen, Y. and Xu, C.J. (2015) Global Expo-nential Stability in a Lagrange Sense for Memristive Recurrent Neural Networks with Time-Varying Delays. Neuro-computing, 149, 1330-1336.
 Liao, X.X. (2000) Theory and Application of Stability for Dynamical System. National Defense Publishing House, Beijing.
Filippov, A.F. (1988) Differential Equations with Discontinuous Right-Hand Sides. Kluwer, Dordrecht.