zbMATH — the first resource for mathematics

Robust stability analysis of generalized neural networks with discrete and distributed time delays. (English) Zbl 1142.93401
Summary: This paper is concerned with the problem of robust global stability analysis for generalized neural networks (GNNs) with both discrete and distributed delays. The parameter uncertainties are assumed to be time-invariant and bounded, and belong to given compact sets. The existence of the equilibrium point is first proved under mild conditions, assuming neither differentiability nor strict monotonicity for the activation function. Then, by employing a Lyapunov-Krasovskii functional, the addressed stability analysis problem is converted into a convex optimization problem, and a linear matrix inequality (LMI) approach is utilized to establish the sufficient conditions for the globally robust stability for the GNNs, with and without parameter uncertainties. These conditions can be readily checked by utilizing the Matlab LMI toolbox. A numerical example is provided to demonstrate the usefulness of the proposed global stability condition.

93D09 Robust stability
34K20 Stability theory of functional-differential equations
92B20 Neural networks for/in biological studies, artificial life and related topics
Matlab; LMI toolbox
Full Text: DOI
[1] Arik, S., Stability analysis of delayed neural networks, IEEE trans circ syst—I, 47, 1089-1092, (2000) · Zbl 0992.93080
[2] Baldi, P.; Atiya, A.F., How delays affect neural dynamics and learning, IEEE trans neural networks, 5, 612-621, (1994)
[3] Boyd, S.; Ghaoui, L.E.; Feron, E.; Balakrishnan, V., Linear matrix inequalities in system and control theory, (1994), SIAM Philadelphia · Zbl 0816.93004
[4] Cao, J., Periodic oscillation and exponential stability of delayed cnns, Phys lett A, 270, 157-163, (2000)
[5] Cao, J.; Ho, D.W.C., A general framework for global asymptotic stability analysis of delayed neural networks based on LMI approach, Chaos, solitons & fractals, 24, 1317-1329, (2005) · Zbl 1072.92004
[6] Cao, J.; Huang, D.S.; Qu, Y., Global robust stability of delayed recurrent neural networks, Chaos, solitons & fractals, 23, 221-229, (2005) · Zbl 1075.68070
[7] Cao, J.; Chen, T., Globally exponentially robust stability and periodicity of delayed neural networks, Chaos, solitons & fractals, 22, 957-963, (2004) · Zbl 1061.94552
[8] Cao, J.; Liang, J.; Lam, J., Exponential stability of high-order bidirectional associative memory neural networks with time delays, Phys D: nonlinear phenomena, 199, 425-436, (2004) · Zbl 1071.93048
[9] Chen, A.; Cao, J.; Huang, L., Global robust stability of interval cellular neural networks with time-varying delays, Chaos, solitons & fractals, 23, 787-799, (2005) · Zbl 1101.68752
[10] Gao, H.; Wang, C., Robust L2−L∞ filtering for uncertain systems with multiple time-varying state delays, IEEE trans circ syst—part I, 50, 4, 594-599, (2003) · Zbl 1368.93712
[11] Gao, H.; Wang, C., A delay-dependent approach to robust H∞ filtering for uncertain discrete-time state-delayed systems, IEEE trans signal process, 52, 6, 1631-1640, (2004) · Zbl 1369.93175
[12] Huang, H.; Cao, J.; Qu, Y., Global robust stability of delayed neural networks with a class of general activation functions, J comput syst sci, 69, 4, 688-700, (2004) · Zbl 1076.68060
[13] Huang, H.; Ho, D.W.C.; Cao, J., Analysis of global exponential stability and periodic solutions of neural networks with time-varying delays, Neural networks, 18, 161-170, (2005) · Zbl 1078.68122
[14] Joy, M.P., On the global convergence of a class of functional differential equations with applications in neural network theory, J math anal appl, 232, 61-81, (1999) · Zbl 0958.34057
[15] Joy, M.P., Results concerning the absolute stability of delayed neural networks, Neural networks, 13, 613-616, (2000)
[16] Liang, J.; Cao, J., Global asymptotic stability of bi-directional associative memory networks with distributed delays, Appl math comput, 152, 415-424, (2004) · Zbl 1046.94020
[17] Liu Y, Wang Z, Liu X. Global exponential stability of generalized recurrent neural networks with discrete and distributed delays. Neural Networks, in press. · Zbl 1102.68569
[18] Liu, Z.; Chen, A.; Huang, L., Periodic oscillatory solution to delayed BAM neural networks with impulses, Int J nonlinear sci numer simul, 5, 4, 355-362, (2004) · Zbl 1401.34043
[19] Morita, M., Associative memory with nonmonotone dynamics, Neural networks, 6, 6, 115-126, (1993)
[20] Ruan, S.; Filfil, R.S., Dynamics of a two-neuron system with discrete and distributed delays, Physica D, 191, 323-342, (2004) · Zbl 1049.92004
[21] Song, Q.; Cao, J.; Zhao, Z., Periodic solutions and its exponential stability of reaction-diffusion recurrent neural networks with continuously distributed delays, Nonlinear anal: real world appl, 7, 1, 65-80, (2006) · Zbl 1094.35128
[22] Van den Driessche, P.; Zou, X., Global attractivity in delayed Hopfield neural networks model, SIAM J appl math, 58, 1878-1890, (1998) · Zbl 0917.34036
[23] Wang, Z.; Ho, D.W.C.; Liu, X., State estimation for delayed neural networks, IEEE trans neural networks, 16, 279-284, (2005)
[24] Wang, Z.; Liu, Y.; Liu, X., On global asymptotic stability of neural networks with discrete and distributed delays, Phys lett A, 345, 299-308, (2005) · Zbl 1345.92017
[25] Xu, S.; Lam, J.; Ho, D.W.C., Global robust exponential stability analysis for interval recurrent neural networks, Phys lett A, 325, 124-133, (2004) · Zbl 1161.93335
[26] Zhang, Y., Global exponential stability and periodic solutions of delay Hopfield neural networks, Int J syst sci, 27, 227-231, (1996) · Zbl 0845.93071
[27] Zhao, H., Global asymptotic stability of Hopfield neural network involving distributed delays, Neural networks, 17, 47-53, (2004) · Zbl 1082.68100
[28] Zhao, H., Existence and global attractivity of almost periodic solution for cellular neural network with distributed delays, Appl math comput, 154, 683-695, (2004) · Zbl 1057.34099
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.