Abstract
Exponential periodicity of continuous-time neural networks with delays is investigated. Without assuming the boundedness and differentiability of the activation functions, some new sufficient conditions ensuring existence and uniqueness of periodic solution for a general class of neural systems are obtained. Discrete-time analogue of the continuous-time system with periodic input is formulated and we study their dynamical characteristics. The exponential periodicity of the continuous-time system is preserved by the discrete-time analogue without any restriction imposed on the uniform discretization step-size.
Similar content being viewed by others
References
Bouzerman, A. and Pattison, T.: Neural network for quadratic optimization with bound constraints. IEEE Trans. Neural Networks 4 (1993), 293–303.
Michel, A. N., Farrel, J. and Porod, W.: Qualitative analysis of neural networks. IEEE Trans. Circuits Systems I 37(Oct. 1989), 229–243.
Cao, J.: On exponential stability and periodic solutions of CNNs with delays. Physics Letters A 267 (2000), 312–318.
Cao, J.: On exponential stability and periodic solutions of delayed celluler neural networks. Science in China 30(6) (2000), 541–549.
Liao, X. and Wang, J.: Algebraic criteria for global exponential stability of cellular neural networks with multiple time delays. IEEE Trans. Circuits Systems I 50(2) (2003), 268–275.
Forti, M.: On global asymptotic stability of a class of nonlinear systems arising in neural network theory. Journal of differential equations 113 (1994), 246–264.
Forti, M. and Tesi, A.: New conditions for global stability of neural networks with application to linear and quadratic programming Problems. IEEE Trans. Circuits and Systems I 42(1995), 354–366.
Venetianer, P. L. and Roska, T.: Image compression by delayed CNNs. IEEE Trans. Circuits Syst. I 45 (1998), 205–215.
Sudharsanan, S. and Sundareshan, M.: Exponential stability and a systematic synthesis of a neural network for quadratic minimization, Neural networks 4 (1991), 599–613.
Morita, M.: Associative memory with non-monntone dynamics. Neural networks 6 (1993), 115–126.
Tank, D. W. and Hopfield J. J.: Simple ‘neural’ optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit, IEEE Trans. Circuits & Systems 33 (1986), 533–541.
Kennedy, M. and Chua, L.: Neural networks for linear and nonlinear programming. IEEE Trans. Circuits & Systems 35 (1988), 554–562.
Townley, S. et al.: Existence and learning of oscillations in recurrent neural networks. IEEE Trans. Neural Networks 11 (2000), 205–214.
Chen, Y. H. and Fang, S. C.: Neurocomputing with time delay analysis for solving convex quadratic programming problems. IEEE Trans. Neural Networks 11 (2000), 230–234.
Zhang, Y., Pheng, H. A. and Vadakkepat, P.: Absolute periodicity and absolute stability of delayed neural networks. IEEE Trans. Circuits and Systems: I 49 (2002), 256–261.
Sun, C., Song, S. and Feng, C. B.: On global robust exponential stability of interval neural networks with delays, Proceedings of the 2002 International Joint Conference on Neural Networks. Hawaii, 3, 2738–2742, 2002.
Sun, C., Fei, S., Zhang, K., Cao, J. and Feng, C. B.: On absolute exponential stability of a class of neural networks, Proceedings of 15th International Federation of Automatic Contorl (IFAC'02). Barcelona, Spain, July 21-26, 2002.
Sun, C. and Feng, C. B.: On exponential periodicity of delayed neural networks. In: Proceedings of the 2003 IEEE International Symposium on Circuits and Systems, May 25-28, pp. 681–684.
Sun, G. and Sun, C.: On absolute stability of delayed neural networks, Proceedings of The International Conference on Communication Circuits and Systems & West Sino-Expo 2002, pp. 1675–1679, 2002.
Sun, C. and Feng, C. B.: On exponential stability of delayed neural networks with globally lipschitz continuous activation functions. In: Proceedings of the 4th World Congress on Intelligent Control and Automation. Shanghai, Vol. 3, June 2002, pp. 1953–1957.
Sun, C., Zhang, K., Fei, S. and Feng, C. B.: On exponential stability of delayed neural networks with a general class of activation functions. Physics Letters A. 298(2/3) 2002, 122–132.
Sun, C. and Feng, C. B.: Global robust exponential stability of interval neural networks with delays. Neural Processing Letters 17(1) (2003), 107–115.
Sun, C., Liu, D. and Feng, C. B.: New results on exponential periodicity of delayed neural networks. In: Proceedings of the 2003 IEEE Joint Conference on Neural Networks (IJCNN'2003) pp. 902–907 Portland, Oregon, 2003.
Arik, S. and Tavsanoglu, V.: On the global asymptotic stability of delayed cellular neural networks. IEEE Trans. Circuits and Systems: I 47(4) (2000), 571–574.
Gopalsamy, K. and He, X. Z.: Stability in asymmetric Hopfield nets with transmission delays. Physica D 76 (1994), 344–358.
Gopalsamy, K. and He, X. Z.: Delay-independent stability in bi-directional associative memory networks. IEEE Trans. Neural Networks 5 (1994), 998–1002.
Mohamad, S. and Gopalsamy, K.: Exponential stability of contiuous-time and discretetime cellular neural networks with delays. Applied Mathematics and Computation 135 (2003), 17–38.
Mohamad, S.: Global exponential stability in continuous-time and discrete-time delay bi-directional neural networks. Physical D 159 (2001), 233–251.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Sun, C., Feng, CB. Exponential Periodicity of Continuous-time and Discrete-Time Neural Networks with Delays. Neural Processing Letters 19, 131–146 (2004). https://doi.org/10.1023/B:NEPL.0000023421.60208.30
Issue Date:
DOI: https://doi.org/10.1023/B:NEPL.0000023421.60208.30