Passivity analysis of stochastic delayed neural networks with Markovian switching
Introduction
In the past decades, neural networks have been extensively used in signal processing, pattern recognition, associate memories, control, and other areas. Some of these applications require that the equilibrium points of the designed network be stable. So, it is important to study the stability of neural networks. In reality, time-delay are frequently encountered in neural networks, where a time delay is often a source of instability and oscillations. Recently, lots of sufficient conditions have been proposed to verify the asymptotical or exponential stability of delayed neural networks, see [6], [8], [14], [16], [21], [22], [26], [27], [28], [34], [35], [36], [37], [39], [40] and the references cited therein for some recent publications.
In implementation or applications of neural networks, it is not uncommon for the parameters of neural networks (e.g. connection weights and biases) change abruptly due to unexpected failure or designed switching [17]. In such a case, neural networks can be represented by a switching model which can be regarded as a set of parametric configurations switching from one to another according to a given Markovian chain. On the other hand, when one models real nervous systems, stochastic disturbances and parameter uncertainties are unavoidable to consider. Because in real nervous system, synaptic transmission is a noisy process brought on by random fluctuation from the release of neurotransmitters, and in hardware implementation of neural networks, the network parameters of the neural system may be subjected to some changes due to the tolerances of electronic components employed in the design. The robust stability of several stochastic switching neural networks with time delays was analyzed [13], [24], [32], [35].
The passivity theory intimately related to the circuit analysis method [3] has played an important role in the analysis of the stability of dynamical system, complexity, signal processing, chaos control and synchronization and fuzzy control [1], [5], [7], [11], [25], [29], [31]. In the first place, many systems need to be passive in order to attenuate noises effectively. In the second place, the robustness measure (such as robust stability or robust performance) of a system often reduces to a subsystem or a modified system that is passive. Passivity analysis is a major tool for studying stability of uncertain or nonlinear systems, especially for high-order systems, and thus the passivity analysis approach has been used in control problems for a long time to deal with robust stability problems for complex uncertain systems. The essence of the passivity theory is that the passive properties of a system can keep the system's internal stability. Recently, many authors have studied the passivity of delayed systems [9], [11], [12], [18], [19], [31], [37] and the passivity of delayed neural networks [4], [10], [15], [20], [23], [30], [33], [38], because it can lead to general conclusions on the stability using only input–output characteristics. In the stochastic neural networks, most authors have not considered the input vector in diffusion part. To the best of our knowledge, however, few authors have considered the passivity conditions for stochastic delayed neural networks with Markovian switching.
Motivated by the above discussions, in this paper, we investigate the robust passivity of stochastic delayed neural networks with Markovian switching. The parameter uncertainties are norm-bounded. By utilizing Lyapunov–Krasovskii functional and free-weighting matrix, a unified linear matrix inequality (LMI) approach is developed to establish sufficient conditions for neural networks to be robust passivity. Note that LMIs can be easily solved by using the Matlab LMI toolbox, and no tuning of parameters is required [2]. It is worth mentioning that the passivity criteria of the neural networks with Markovian switching include the passivity criteria of neural networks without Markovian switching as special cases [10], [23]. An example is provided to show the validity of the proposed passivity conditions.
Notations: The notations are quite standard. Throughout this paper, Rn and denote, respectively, the n-dimensional Euclidean space and the set of all real matrices. WT and W−1 denote, respectively, the transpose of, and inverse of a square matrix W. The notation (respectively, ), where X is symmetric matrices, means that X is positive semidefinite (respectively, positive definite). In is the n×n identity matrix. is the Euclidean norm in Rn, is the operator norm of a square matrix. The shorthand diag denotes a block diagonal matrix with diagonal blocks being the matrices . Moreover, let be a complete probability space with a filtration satisfying the usual conditions (i.e. the filtration contains all p-null sets and is right continuous). w(t) be a scalar Brownian motion defined on the probability space. is the mathematical expectation operator with respect to the given probability measure P. Sometimes, the arguments of a function or a matrix will be omitted in the analysis when no confusion can arise.
Section snippets
Problem formulation
Let , be a right-continuous Markov chain on the probability space taking values in a finite state space with generator given by where . Here is the transition rate from i to j if , while . We assume that the Markov chain is independent of the Brown motion . It is known that almost every sample path of r(t) is a right-continuous step function with a finite number of simple jumps in
Delay-dependent passivity condition
Firstly, we analyze the delay-dependent passivity of stochastic delayed neural networks with Markovian switching of (1), (2). Theorem 1 The stochastic delayed neural network with Markovian switching of (1), (2) is passive, if there exist positive definite matrices Pi,Qi,Ri,Ni,Zi,Ui, positive diagonal matrices , scalar and , , such that the
Delay-independent passivity condition
Now, in this section, we concentrate on the delay-independent passivity analysis of stochastic switching delayed neural networks (1), (2) with . Theorem 2 The stochastic delayed uncertain neural networks with Markovian switching of (1), (2) is passive, if there exist positive definite matrices Pi,Q, positive diagonal matrices , and scalar , , , such that the coupled LMIs hold
Numerical example
In this section, we give a numerical example to illustrate the effectiveness of the obtain passive results. Example Consider a two-neuron stochastic neural networks in the form of (1), (2) with time delay and Markovian switching, where activation function isObviously, this activation function satisfies the vector condition with K=I and the time delay be . So, we have . Let
Conclusions
In this paper, the robust passivity of stochastic delayed neural networks with Markovian switching were studied by the Lyapunov functional method, and the passivity criteria have been given in terms of LMIs. A simple example has been used to demonstrate that the theoretical results are correct and effective.
Acknowledgments
This paper was supported by the National Science Foundation of China with Grant nos. 60874031 and 60740430664 and the Specialized Research Fund for the Doctoral Program of Higher Education of China 2007048750 and 20090142110040.
Song Zhu was born in 1982. He received the B.S. degree in Mathematics in 2004 from Xuzhou Normal University, Xuzhou, China, the M.S. degree in Probability and Mathematical Statistics in 2007, Ph.D. degree in System Engineering in 2010, from Huazhong University of Science and Technology, Wuhan, China, respectively. He is currently with the College of Sciences, China University of Mining and Technology, Xuzhou, China. His research is concerned with neural networks and stochastic differential
References (40)
- et al.
Passivity analysis for uncertain neural networks with discrete and distributed time-varying delays
Phys. Lett. A
(2009) Passivity approach to fuzzy control systems
Automatica
(1998)- et al.
Mean square exponential stability of uncertain stochastic delayed neural networks
Phys. Lett. A
(2008) - et al.
On passivity analysis for stochastic neural networks with interval time-varing delay
Neurocomputing
(2010) - et al.
Robust stability analysis of switched Hopfield neural networks with time-varying delay under uncertainty
Phys. Lett. A
(2005) - et al.
Delay-interval-dependent stability of recurrent neural networks with time-varying delay
Neurocomputing
(2009) - et al.
A global exponential robust stability criterion for interval delayed neuralnetworks with variable delays
Neurocomputing
(2006) - et al.
Passivity and absolute stabilization of a class of discrete time nonlinear systems
Automatica
(1995) - et al.
Passivity analysis of integro-differential neural networks with time-varying delays
Neurocomputing
(2007) - et al.
Global exponential stability of generalized recurrent neural networks with discrete and distributed delays
Neural Networks
(2006)
Passivity analysis of discrete-time stochastic networks with time-varying delays
Neurocomputing
Robust exponential stability analysis of neural networks with multiple time delays
Neurocomputing
Robust stability criteria for interval Cohen–Grossberg neural networks with time varying delay
Neurocomputing
Improved delay-dependent exponential stability criteria for discrete-time recurrent neural networks with time-varying delays
Neurocomputing
Passivity and stability of switched systems: a multiple storage function method
Syst. Control Lett.
New passivity criteria for neural networks with time-varying delay
Neural Networks
Passivity as a design tool for group coordination
IEEE Trans. Automat. Control
Linear Matrix Inequalities in System and Control Theory
Classical Network Synthesis
Global asymptotical stability of recurrent neural networks with multiple discrete delays and distributed delays
IEEE Trans. Neural Networks
Cited by (45)
Robust stability of uncertain stochastic complex-valued neural networks with additive time-varying delays
2020, Mathematics and Computers in SimulationCitation Excerpt :Thus, when we investigate the stability analysis of NNs, the stochastic disturbance cannot be ignored. As a consequence, many researchers have been published several scientific results regarding the stability of NNs with stochastic disturbance recently [2,6,21,26,28,37–40]. For example, the LKF approach has been employed to formulate a novel robust exponential stability criterion for Markovian jump impulsive stochastic Cohen–Grossberg neural networks with mixed time delays to be achieved in the work [38].
Global asymptotic stability of stochastic complex-valued neural networks with probabilistic time-varying delays
2020, Mathematics and Computers in SimulationPassive control for singular time-delay system with actuator saturation
2016, Applied Mathematics and Computation
Song Zhu was born in 1982. He received the B.S. degree in Mathematics in 2004 from Xuzhou Normal University, Xuzhou, China, the M.S. degree in Probability and Mathematical Statistics in 2007, Ph.D. degree in System Engineering in 2010, from Huazhong University of Science and Technology, Wuhan, China, respectively. He is currently with the College of Sciences, China University of Mining and Technology, Xuzhou, China. His research is concerned with neural networks and stochastic differential equations.
Yi Shen received the Ph.D. degree from Huazhong University of Science and Technology, Wuhan, China, in 1998. He was a Postdoctoral Research Fellow at the Huazhong University of Science and Technology during 1999–2001. He joined the Department of Control Science and Engineering, Huazhong University of Science and Technology, and became an Associate Professor in 2001 and was promoted as Professor in 2005. From 2006 to 2007, he was a Postdoctoral Research Fellow at the Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong. He has authored over 80 research papers. His main research interests lie in the fields of stochastic control and neural networks.