State estimation for jumping recurrent neural networks with discrete and distributed delays

This paper is concerned with the state estimation problem for a class of Markovian neural networks with discrete and distributed time-delays. The neural networks have a finite number of modes, and the modes may jump from one to another according to a Markov chain. The main purpose is to estimate the neuron states, through available output measurements, such that for all admissible time-delays, the dynamics of the estimation error is globally asymptotically stable in the mean square. An effective linear matrix inequality approach is developed to solve the neuron state estimation problem. Both the existence conditions and the explicit characterization of the desired estimator are derived. Furthermore, it is shown that the traditional stability analysis issue for delayed neural networks with Markovian jumping parameters can be included as a special case of our main results. Finally, numerical examples are given to illustrate the applicability of the proposed design method.

[1]  Zidong Wang,et al.  On global asymptotic stability of neural networks with discrete and distributed delays , 2005 .

[2]  James L. McClelland,et al.  Finite State Automata and Simple Recurrent Networks , 1989, Neural Computation.

[3]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[4]  Mike Casey,et al.  The Dynamics of Discrete-Time Computation, with Application to Recurrent Neural Networks and Finite State Machine Extraction , 1996, Neural Computation.

[5]  Peter Ti.  Markovian Architectural Bias of Recurrent Neural Networks , 2004 .

[6]  Yung C. Shin,et al.  Radial basis function neural network for approximation and estimation of nonlinear stochastic dynamic systems , 1994, IEEE Trans. Neural Networks.

[7]  Zidong Wang,et al.  Synchronization and State Estimation for Discrete-Time Complex Networks With Distributed Delays , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[8]  D. Elworthy.  ASYMPTOTIC METHODS IN THE THEORY OF STOCHASTIC DIFFERENTIAL EQUATIONS , 1992 .

[9]  Jinde Cao,et al.  Global output convergence of recurrent neural networks with distributed delays , 2007 .

[10]  Hongyong Zhao,et al.  Global exponential stability and periodicity of cellular neural networks with variable delays , 2005 .

[11]  Yurong Liu,et al.  On delay-dependent robust exponential stability of stochastic neural networks with mixed time delays and Markovian switching , 2008 .

[12]  Jinde Cao,et al.  Boundedness and stability for recurrent neural networks with variable coefficients and time-varying delays , 2003 .

[13]  Matevž Kovačič,et al.  Timetable construction with Markovian neural network , 1993 .

[14]  H. Chizeck,et al.  Controllability, stabilizability, and continuous-time Markovian jump linear quadratic control , 1990 .

[15]  S. Arik.  Stability analysis of delayed neural networks , 2000 .

[16]  K. Gu.  An integral inequality in the stability problem of time-delay systems , 2000, Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187).

[17]  Zidong Wang,et al.  Nonlinear filtering for state delayed systems with Markovian switching , 2002, Proceedings of the 4th World Congress on Intelligent Control and Automation (Cat. No.02EX527).

[18]  Huijun Gao,et al.  New Results on Stability of Discrete-Time Systems With Time-Varying State Delay , 2007, IEEE Transactions on Automatic Control.

[19]  Zidong Wang,et al.  Robust stability for stochastic Hopfield neural networks with time delays , 2006 .

[20]  Huijun Gao,et al.  Parameter-dependent robust stability of uncertain time-delay systems , 2007 .

[21]  Lothar Litz,et al.  Estimation of unmeasured inputs using recurrent neural networks and the extended Kalman filter , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[22]  E. Yaz.  Linear Matrix Inequalities In System And Control Theory , 1998, Proceedings of the IEEE.

[23]  Huaguang Zhang,et al.  Global Asymptotic Stability of Recurrent Neural Networks With Multiple Time-Varying Delays , 2008, IEEE Transactions on Neural Networks.

[24]  James Lam,et al.  A new delay system approach to network-based control , 2008, Autom..

[25]  Mark P. Joy,et al.  Results concerning the absolute stability of delayed neural networks , 2000, Neural Networks.

[26]  Jinde Cao,et al.  Convergence of Discrete-Time Recurrent Neural Networks with Variable Delay , 2005, Int. J. Bifurc. Chaos.

[27]  Yoshua Bengio,et al.  The problem of learning long-term dependencies in recurrent networks , 1993, IEEE International Conference on Neural Networks.

[28]  Daniel W. C. Ho,et al.  State estimation for delayed neural networks , 2005, IEEE Transactions on Neural Networks.

[29]  Hongyong Zhao,et al.  Global asymptotic stability of Hopfield neural network involving distributed delays , 2004, Neural Networks.

[30]  Amir F. Atiya,et al.  How delays affect neural dynamics and learning , 1994, IEEE Trans. Neural Networks.

[31]  Jian-an Fang,et al.  Global stability of stochastic high-order neural networks with discrete and distributed delays , 2008 .

[32]  F. Salam,et al.  Adaptive neural observer with forward co-state propagation , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[33]  Stephen P. Boyd,et al.  Linear Matrix Inequalities in Systems and Control Theory , 1994 .

[34]  Jinde Cao,et al.  On global asymptotic stability of recurrent neural networks with time-varying delays , 2003, Appl. Math. Comput..

[35]  Zidong Wang,et al.  Global exponential stability of generalized recurrent neural networks with discrete and distributed delays , 2006, Neural Networks.

[36]  Désiré Bollé,et al.  On the overlap dynamics of multi-state neural networks with a finite number of patterns , 1992 .