×

Absolute exponential stability of recurrent neural networks with Lipschitz-continuous activation functions and time delays. (English) Zbl 1074.68049

Summary: This paper investigates the absolute exponential stability of a general class of delayed neural networks, which require the activation functions to be partially Lipschitz continuous and monotone nondecreasing only, but not necessarily differentiable or bounded. Three new sufficient conditions are derived to ascertain whether or not the equilibrium points of the delayed neural networks with additively diagonally stable interconnection matrices are absolutely exponentially stable by using delay Halanay-type inequality and Lyapunov function. The stability criteria are also suitable for delayed optimization neural networks and delayed cellular neural networks whose activation functions are often nondifferentiable or unbounded. The results herein answer a question: if a neural network without any delay is absolutely exponentially stable, then under what additional conditions, the neural networks with delay is also absolutely exponentially stable.

MSC:

68T05 Learning and adaptive systems in artificial intelligence
PDF BibTeX XML Cite
Full Text: DOI

References:

[1] Arik, S.; Tavsanoglu, V., A comment on comments on necessary and sufficient condition for absolute stability of neural networks, IEEE trans circuits syst. I, 45, 595-596, (1998) · Zbl 0917.68223
[2] Arik, S.; Tavsanoglu, V., Equilibrium analysis of delayed cnns, IEEE trans circuits syst. I, 45, 168-171, (1998)
[3] Belair, J.; Campbell, S.A.; Driessche, P.V.D., Frustration, stability and delayed-induced oscillations in a neural network model, SIAM J. appl. math., 56, 245-255, (1996) · Zbl 0840.92003
[4] Bouzerman, A.; Pattison, T.R., Neural network for quadratic optimization with bound constraints, IEEE trans neural networks, 4, 293-303, (1993)
[5] Butcher, J.C., The numerical analysis of ordinary differential equations, (1987), Wiley Chichester · Zbl 0616.65072
[6] Cao, J., Global stability analysis in delayed cellular neural networks, Physical review E, 59, 5940-5944, (1999)
[7] Cao, J., Periodic oscillation and exponential stability of delayed cnns, Physics letters A, 270, 157-163, (2000)
[8] Cao, J., A set of stability criteria for delayed cellular neural networks, IEEE trans circuits syst. I, 48, 494-498, (2001) · Zbl 0994.82066
[9] Cao, J., Global stability conditions for delayed cnns, IEEE trans circuits syst. I, 48, 1330-1333, (2001) · Zbl 1006.34070
[10] Cao, J.; Li, Q., On the exponential stability and periodic solution of delayed cellular neural networks, Journal of mathematical analysis and applications, 252, 50-64, (2000) · Zbl 0976.34067
[11] Cao, J.; Wang, L., Periodic oscillatory solution of bidirectional associative memory networks with delays, Physical review E, 61, 1825-1828, (2000)
[12] Cao, J.; Zhou, D., Stability analysis of delayed cellular neural networks, Neural networks, 11, 1601-1605, (1998)
[13] Chua, L.O.; Wang, N.N., On the application of degree theory to the analysis of resistive nonlinear networks, Int. J. circuit theory applicat., 5, 45-68, (1977) · Zbl 0342.94013
[14] Cronin, J., Fixed points and topological degree in nonlinear analysis, (1964), American Mathematical Society Providence, RI · Zbl 0117.34803
[15] Fiedler, M.; Pták, V., Some generalizations of positive definiteness and monotonicity, Numer. math., 9, 163-172, (1966) · Zbl 0148.25801
[16] Forti, M., A note on neural networks with multiple equilibrium points, IEEE trans circuits syst. I, 43, 487-491, (1996)
[17] Forti, M.; Manetti, S.; Marini, M., Necessary and sufficient condition for absolute stability of neural networks, IEEE trans circuits syst. I, 41, 491-494, (1994) · Zbl 0925.92014
[18] Forti, M.; Liberatore, A.; Manetti, S.; Marini, M., On absolute stability of neural networks, Proceedings of the 1994 IEEE international symposium circuit systems, 6, 241-244, (1994)
[19] Forti, M.; Tesi, A., New conditions for global stability of neural networks with application to linear and quadratic programming problems, IEEE trans circuits syst. I, 42, 354-366, (1995) · Zbl 0849.68105
[20] Kaszkurewicz, E.; Bhaya, A., On a class of globally stable neural circuits, IEEE trans circuits syst. I, 41, 171-174, (1994) · Zbl 0843.93063
[21] Kaszkurewicz, E.; Bhaya, A., Comments on necessary and sufficient condition for absolute stability of neural networks, IEEE trans circuits syst. I, 42, 497-499, (1995) · Zbl 0850.93698
[22] Liang, X.B.; Wang, J., A proof of kaszkurewicz and Bhaya’s conjecture on absolute stability of neural networks in two-neuron case, IEEE trans circuits syst. I, 47, 609-611, (2000) · Zbl 1050.92500
[23] Liang, X.B.; Wang, J., Absolute exponential stability of neural networks with a general class of activation functions, IEEE trans circuits syst. I, 47, 1258-1263, (2000) · Zbl 1079.68592
[24] Liang, X.B.; Wang, J., An additive diagonal stability condition for absolute exponential stability of a general class of neural networks, IEEE trans circuits syst. I, 48, 1308-1317, (2001) · Zbl 1098.62557
[25] Liang, X.B.; Wu, L.D., Comments on new conditions for global stability of neural networks with application to linear and quadratic programming problems, IEEE trans circuits syst. I, 44, 1099-1101, (1997)
[26] Liang, X.B.; Wu, L.D., A simple proof of a necessary and sufficient condition for absolute stability of symmetric neural networks, IEEE trans circuits syst. I, 45, 1010-1011, (1998) · Zbl 1055.93548
[27] Liang, X.B.; Wu, L.D., A comment on comments on necessary and sufficient condition for absolute stability of neural networks, IEEE trans circuits syst. I, 45, 594, (1998) · Zbl 0925.92015
[28] Liang, X.B.; Wu, L.D., Global exponential stability of a class of neural circuits, IEEE trans circuits syst. I, 46, 748-751, (1999) · Zbl 0952.94008
[29] Liang, X.B.; Yamaguchi, T., Necessary and sufficient condition for absolute exponential stability of a class of nonsymmetric neural networks, IEICE trans inf. and syst., E80, 802-807, (1997)
[30] Liang, X.B.; Yamaguchi, T., On the analysis of global and absolute stability of nonlinear continuous neural networks, IEICE trans fundamentals, E80-A, 223-229, (1997)
[31] Liao, T.-L.; Wang, F.-C., Global stability for cellular neural networks with time delay, IEEE trans neural networks, 11, 1481-1484, (2000)
[32] Marcus, C.M.; Westervelt, R.M., Stability of analog neural networks with delay, Phys. rev. A, 39, 347-359, (1989)
[33] Olien, L.; Belair, J., Bifurcations, stability, and monotonicity properties of a delayed neural network model, Physica D, 102, 349-363, (1997) · Zbl 0887.34069
[34] Pakdaman, K.; Grotta-Ragazzo, C.; Malta, C.P.; Arino, O.; Vibert, J.-F., Effect of delay on the boundary of the basin of attraction in a system of two neurons, Neural networks, 11, 509-519, (1998)
[35] Sandberg, I.W.; Willson, A.N., Some theorems on properties of dc equations of nonlinear networks, Bell syst. tech. J., 48, 1-34, (1969)
[36] Sudharsanan, S.I.; Sundareshan, M.K., Exponential stability and a systematic synthesis of a neural network for quadratic minimization, Neural networks, 4, 599-613, (1991)
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.