State estimation for jumping recurrent neural networks with discrete and distributed delays. (English) Zbl 1335.93125

Summary: 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.


93E10 Estimation and detection in stochastic control theory
60J20 Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.)
60J75 Jump processes (MSC2010)
92B20 Neural networks for/in biological studies, artificial life and related topics


LMI toolbox
Full Text: DOI Link


[1] Arik, S., Stability analysis of delayed neural networks, IEEE transactions on circuits systems -I, 47, 1089-1092, (2000) · Zbl 0992.93080
[2] Baldi, P.; Atiya, A.F., How delays affect neural dynamics and learning, IEEE transactions on neural networks, 5, 612-621, (1994)
[3] Bengio, Y.; Frasconi, P.; Simard, P., The problem of learning long-term dependencies in recurrent networks, (), 1183-1188
[4] Bolle, D.; Dupont, P.; Vinck, B., On the overlap dynamics of multi-state neural networks with a finite number of patterns, Journal of physics A, 25, 2859-2872, (1992) · Zbl 0800.82013
[5] Boyd, S.; Ghaoui, L. EI; Feron, E.; Balakrishnan, V., Linear matrix inequalities in system and control theory, (1994), SIAM Philadephia
[6] Casey, M.P., The dynamics of discrete-time computation with application to recurrent neural networks and finite state machine extraction, Neural computation, 8, 6, 1135-1178, (1996)
[7] Cleeremans, A.; Servan-Schreiber, D.; McClelland, J.L., Finite state automata and simple recurrent networks, Neural computation, 1, 3, 372-381, (1989)
[8] Elanayar, V.T.S.; Shin, Y.C., Approximation and estimation of nonlinear stochastic dynamic systems using radial basis function neural networks, IEEE transactions on neural networks, 5, 4, 594-603, (1994)
[9] Elman, J.L., Finding structure in time, Cognitive science, 14, 179-211, (1990)
[10] Gahinet, P.; Nemirovsky, A.; Laub, A.J.; Chilali, M., LMI control toolbox: for use with Matlab, (1995), The MATH Works Inc
[11] Gao, H.; Chen, T.; Lam, J., A new delay system approach to network-based control, Automatica, 44, 1, 39-52, (2008) · Zbl 1138.93375
[12] Gao, H.; Shi, P.; Wang, J., Parameter-dependent robust stability of uncertain time-delay systems, Jorunal of computational and applied mathematics, 206, 1, 366-373, (2007) · Zbl 1136.93030
[13] Gao, H.; Chen, T., New results on stability of discrete-time systems with time-varying state delay, IEEE transactions on automatic control, 52, 2, 328-334, (2007) · Zbl 1366.39011
[14] Gu, K. (2000). An integral inequality in the stability problem of time-delay systems. In Proceedings of 39th IEEE conference on decision and control, December 2000, Sydney, Australia, (pp. 2805-2810)
[15] Habtom, R.; Litz, L., Estimation of unmeasured inputs using recurrent neural networks and the extended Kalman filter, (), 2067-2071
[16] Huang, H.; Cao, J., On global asymptotic stability of recurrent neural networks with time-varying delays, Applied mathematics and computation, 142, 1, 143-154, (2003) · Zbl 1035.34081
[17] Ji, Y.; Chizeck, H.J., Controllability, stabilizability, and continuous-time Markovian jump linear quadratic control, IEEE transactions on automatic control, 35, 777-788, (1990) · Zbl 0714.93060
[18] Joy, M.P., Results concerning the absolute stability of delayed neural networks, Neural networks, 13, 613-616, (2000)
[19] Kovacic, M., Timetable construction with Markovian neural network, European journal of operational research, 69, 1, 92-96, (1993) · Zbl 0784.90038
[20] Liang, J.; Cao, J., Boundedness and stability for recurrent neural networks with variable coefficients and time-varying delays, Physics letters A, 318, 1-2, 53-64, (2003) · Zbl 1037.82036
[21] Liang, J.; Cao, J., Global output convergence of recurrent neural networks with distributed delays, Nonlinear analysis — real world applications, 8, 1, 187-197, (2007) · Zbl 1114.34056
[22] Liang, J.; Cao, J.; Lam, J., Convergence of discrete-time recurrent neural networks with variable delay, International journal of bifurcation and chaos, 15, 2, 581-595, (2005) · Zbl 1098.68107
[23] Liu, Y.; Wang, Z.; Liu, X., Global exponential stability of generalized recurrent neural networks with discrete and distributed delays, Neural networks, 19, 5, 667-675, (2005) · Zbl 1102.68569
[24] Liu, Y.; Wang, Z.; Liu, X., On delay-dependent robust exponential stability of stochastic neural networks with mixed time delays and Markovian switching, Nonlinear dynamics, 54, 3, 199-212, (2008) · Zbl 1169.92003
[25] Liu, Y.; Wang, Z.; Liang, J.; Liu, X., Synchronization and state estimation for discrete-time complex networks with distributed delays, IEEE transactions on systems, man, and cybernetics — part B, 38, 5, 1314-1325, (2008)
[26] Salam, F. M., & Zhang, J. (2001). Adaptive neural observer with forward co-state propagation. In Proc. international joint conference on neural networks 1, (pp. 675-680)
[27] Skorohod, A.V., Asymptotic methods in the theory of stochastic differential equations, (1989), Amer. Math. Soc Providence, RI
[28] Tino, P.; Cernansky, M.; Benuskova, L., Markovian architectural bias of recurrent neural networks, IEEE transactions on neural networks, 15, 1, 6-15, (2004)
[29] Wang, Z.; Ho, D.W.C.; Liu, X., State estimation for delayed neural networks, IEEE transactions on neural networks, 16, 1, 279-284, (2005)
[30] Wang, Z.; Lam, J.; Liu, X., Nonlinear filtering for state delayed systems with Markovian switching, IEEE transactions on signal processing, 51, 9, 2321-2328, (2003) · Zbl 1369.94314
[31] Wang, Z.; Liu, Y.; Liu, X., On global asymptotic stability of neural networks with discrete and distributed delays, Physics letters A, 345, 4-5, 299-308, (2005) · Zbl 1345.92017
[32] Wang, Z.; Fang, J.; Liu, X., Global stability of stochastic high-order neural networks with discrete and distributed delays, Chaos, solitons & fractals, 36, 2, 388-396, (2008) · Zbl 1141.93416
[33] Wang, Z.; Shu, H.; Fang, J.; Liu, X., Robust stability for stochastic Hopfield neural networks with time delays, Nonlinear analysis — real world applications, 7, 5, 1119-1128, (2006) · Zbl 1122.34065
[34] Zhao, H., Global asymptotic stability of Hopfield neural network involving distributed delays, Neural networks, 17, 47-53, (2004) · Zbl 1082.68100
[35] Zhao, H., Global exponential stability and periodicity of cellular neural networks with variable delays, Physics letters A, 336, 331-341, (2005) · Zbl 1136.34348
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.