- Research
- Open access
- Published:
Sets of generalized exponential stability criteria for switched multilayer dynamic neural networks
Advances in Difference Equations volume 2012, Article number: 150 (2012)
Abstract
This paper investigates new sets of generalized exponential stability criteria for switched multilayer dynamic neural networks. These sets of sufficient stability criteria in forms of linear matrix inequality (LMI) and matrix norm are presented, under which switched multilayer dynamic neural networks reduce the effect of external input to a predefined level. The proposed sets of criteria also guarantee exponential stability for switched multilayer dynamic neural networks without external input.
1 Introduction
Switched systems are a class of hybrid systems consisting of a family of continuous (or discrete) time subsystems and a logical rule that orchestrates the switching between these subsystems. Switched systems have been extensively researched, and several efforts have been focused on the analysis of switched systems [1, 2]. Recently, switched recurrent neural networks were introduced to represent some complex nonlinear systems efficiently by integrating the theory of switched systems with recurrent neural networks [3–6]. Switched dynamic neural networks have found applications in the field of artificial intelligence and high speed signal processing [7, 8]. In [3–6], some stability criteria for switched dynamic neural networks were studied.
There always exist noise disturbances and model uncertainties in real physical systems. Recently, this has led to an interest in a generalized approach [9–19]. The generalized approach has been known as a significant concept to examine the stability of various nonlinear dynamical systems. Here, we have the following natural question: Can we obtain a generalized stability criterion for switched dynamic neural networks. This paper provides an answer to this question. To the best of the authors’ knowledge, the generalized analysis of switched dynamic neural networks has not yet been studied in the literature.
In this paper, we propose new sets of generalized exponential stability criteria for switched multilayer dynamic neural networks. The sets of conditions proposed in this paper are a new contribution to the stability evaluation of switched neural networks. The proposed sets of sufficient stability criteria in forms of linear matrix inequality (LMI) and matrix norm guarantee that switched multilayer dynamic neural networks reduce the effect of external input to a predefined level. This paper is organized as follows. In Section 2, new sets of generalized exponential stability criteria are derived. Finally, conclusions are presented in Section 3.
2 New sets of generalized exponential stability criteria
Consider the following model of switched multilayer neural networks [3]:
where is the state vector, is a linear combination of the states, (, ) is the self-feedback matrix, and are the connection weight matrices, is the nonlinear function vector satisfying the global Lipschitz condition with Lipschitz constant , is an external input vector, and is a known constant matrix. α is a switching signal which takes its values in the finite set . The matrices are allowed to take values, at an arbitrary time, in the finite set . Throughout this paper, we assume that the switching rule α is not known a priori and its instantaneous value is available in real time. Define the indicator function , where
with . By using this indicator function, the model of the switched multilayer neural networks (1)-(2) can be written as
where is satisfied under any switching rules. Let be a predefined level of disturbance attenuation. In this paper, for a given , we derive sets of criteria such that the switched multilayer neural network (3)-(4) with is exponentially stable (, where ) and
under zero-initial conditions for all nonzero , where is the space of square integrable vector functions over .
A set of generalized exponential stability criterion of the switched multilayer neural network (3)-(4) is derived in the following theorem.
Theorem 1 For givenand, the switched multilayer neural network (3)-(4) is generalizedexponentially stable if
for, whereis the minimum eigenvalue of the matrix and P satisfies the Lyapunov inequality.
Proof We consider the Lyapunov function . The time derivative of the function along the trajectory of (3) satisfies
Applying Young’s inequality [20], we have , and . Substituting these inequalities into (10), we have
If the following condition is satisfied,
for , we have
The following inequalities
for , imply the condition (12). Thus, we obtain (6) and (7). Under the zero-initial condition, we have and . Define
Then, for any nonzero , we obtain
From (13), we have . It means
The condition (9) implies
Taking the supremum over leads to (5). This completes the proof. □
Corollary 1 When, the conditions (6)-(9) ensure that the switched multilayer neural network (3)-(4) is exponentially stable.
Proof When , from (13), for all . Thus, for any , it implies that
Finally, we have
This completes the proof. □
In the next theorem, we find a new set of LMI criteria for the generalized exponential stability of the switched multilayer neural network (3)-(4). This set of LMI criteria can be facilitated readily via standard numerical algorithms [21, 22].
Theorem 2 For given leveland, the switched multilayer neural network (3)-(4) is generalizedexponentially stable if there exist a positive symmetric matrix P and a positive scalar ϵ such that
for.
Proof Consider the Lyapunov function . Applying Young’s inequality [20], we have . By using this inequality, the time derivative of along the trajectory of (3) is
If the LMI (19) is satisfied, we have
Under the zero-initial condition, one has and . Define
Then, for any nonzero , we obtain
From (22), we have . It means
The LMI (20) implies
Taking the supremum over leads to (5). This completes the proof. □
Corollary 2 When, a set of LMI conditions (19)-(20) ensure that the switched multilayer neural network (3)-(4) is exponentially stable.
Proof When , from (22), we have
Thus, for any , it implies that
Finally, we have
This completes the proof. □
Example 1 Consider the switched neural network (3)-(4), where
Applying Theorem 2 with , we obtain
The switching signal is given by
where Z is the whole set of nonnegative integers. Figure 1 shows state trajectories when and () is a white noise.
3 Conclusion
In this paper, we have proposed new sets of generalized exponential stability criteria for switched multilayer dynamic neural networks. These sets of sufficient stability criteria are represented by matrix norm and LMI. The proposed sets of criteria ensured that switched multilayer dynamic neural networks attenuate the effect of external input on the state vector. These sets of criteria also guaranteed exponential stability for switched multilayer dynamic neural networks when there is no external input.
References
Lee S, Kim T, Lim J: A new stability analysis of switched systems. Automatica 2000, 36(6):917–922. 10.1016/S0005-1098(99)00208-3
Daafouz J, Riedinger P, Iung C: Stability analysis and control synthesis for switched systems: a switched Lyapunov function approach. IEEE Trans. Autom. Control 2002, 47(11):1883–1887. 10.1109/TAC.2002.804474
Huang H, Qu Y, Li H: Robust stability analysis of switched Hopfield neural networks with time-varying delay under uncertainty. Phys. Lett. A 2005, 345: 345–354. 10.1016/j.physleta.2005.07.042
Yuan K, Cao J, Li H: Robust stability of switched Cohen-Grossberg neural networks with mixed time-varying delays. IEEE Trans. Syst. Man Cybern., Part B, Cybern. 2006, 36(6):1356–1363.
Li P, Cao J: Global stability in switched recurrent neural networks with time-varying delay via nonlinear measure. Nonlinear Dyn. 2007, 49(1–2):295–305. 10.1007/s11071-006-9134-9
Lou X, Cui B: Delay-dependent criteria for robust stability of uncertain switched Hopfield neural networks. Int. J. Autom. Comput. 2007, 4(3):304–314. 10.1007/s11633-007-0304-0
Tsividis, Y: Switched neural networks. US Patent 4873661, 1989
Brown T: Neural networks for switching. IEEE Commun. Mag. 1989, 27(11):72–81.
Grigoriadis K, Watson J:Reduced-order and filtering via linear matrix inequalities. IEEE Trans. Aerosp. Electron. Syst. 1997, 33: 1326–1338.
Watson J, Grigoriadis K: Optimal unbiased filtering via linear matrix inequalities. Syst. Control Lett. 1998, 35: 111–118. 10.1016/S0167-6911(98)00042-5
Palhares R, Peres P: Robust filtering with guaranteed energy-to-peak performance - an LMI approach. Automatica 2000, 36: 851–858. 10.1016/S0005-1098(99)00211-3
Gao H, Wang C:Robust filtering for uncertain systems with multiple time-varying state delays. IEEE Trans. Circuits Syst. I, Fundam. Theory Appl. 2003, 50: 594–599. 10.1109/TCSI.2003.809816
Gao H, Wang C:Delay-dependent robust and filtering for a class of uncertain nonlinear time-delay systems. IEEE Trans. Autom. Control 2003, 48: 1661–1666. 10.1109/TAC.2003.817012
Mahmoud M:Resilient filtering of polytopic systems with state delays. IET Control Theory Appl. 2007, 1: 141–154. 10.1049/iet-cta:20045281
Qiu J, Feng G, Yang J: New results on robust energy-to-peak filtering for discrete-time switched polytopic linear systems with time-varying delay. IET Control Theory Appl. 2008, 2(9):795–806. 10.1049/iet-cta:20070361
Zhou Y, Li J: Energy-to-peak filtering for singular systems: the discrete-time case. IET Control Theory Appl. 2008, 2(9):773–781. 10.1049/iet-cta:20070432
Ahn C: nonlinear system identification via recurrent neural networks. Nonlinear Dyn. 2010, 62: 543–552. 10.1007/s11071-010-9741-3
Ahn C: chaos synchronization. Prog. Theor. Phys. 2010, 123(3):421–430. 10.1143/PTP.123.421
Ahn C:An answer to the open problem of synchronization for time-delayed chaotic systems. Eur. Phys. J. Plus 2012., 127(2): Article ID 22
Arnold V: Mathematical Methods of Classical Mechanics. Springer, New York; 1989.
Boyd S, Ghaoui LE, Feron E, Balakrishinan V: Linear Matrix Inequalities in Systems and Control Theory. SIAM, Philadelphia; 1994.
Gahinet P, Nemirovski A, Laub AJ, Chilali M: LMI Control Toolbox. The Mathworks, Natic; 1995.
Acknowledgements
This research was supported by the MKE (The Ministry of Knowledge Economy), Korea, under the CITRC (Convergence Information Technology Research Center) support program (NIPA-2012-H0401-12-1007) supervised by the NIPA (National IT Industry Promotion Agency).
Author information
Authors and Affiliations
Corresponding author
Additional information
Competing interests
The authors declare that they have no competing interests.
Authors’ contributions
All authors contributed equally and significantly in writing this paper. All authors read and approved the final manuscript.
Authors’ original submitted files for images
Below are the links to the authors’ original submitted files for images.
Rights and permissions
Open Access This article is distributed under the terms of the Creative Commons Attribution 2.0 International License (https://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
About this article
Cite this article
Ahn, C.K., Lee, Y.S. Sets of generalized exponential stability criteria for switched multilayer dynamic neural networks. Adv Differ Equ 2012, 150 (2012). https://doi.org/10.1186/1687-1847-2012-150
Received:
Accepted:
Published:
DOI: https://doi.org/10.1186/1687-1847-2012-150