Skip Navigation Links
Discontinuity, Nonlinearity, and Complexity

Dimitry Volchenkov (editor), Dumitru Baleanu (editor)

Dimitry Volchenkov(editor)

Mathematics & Statistics, Texas Tech University, 1108 Memorial Circle, Lubbock, TX 79409, USA

Email: dr.volchenkov@gmail.com

Dumitru Baleanu (editor)

Cankaya University, Ankara, Turkey; Institute of Space Sciences, Magurele-Bucharest, Romania

Email: dumitru.baleanu@gmail.com


Stability of Hopfield Neural Networks with Delay and Piecewise Constant Argument

Discontinuity, Nonlinearity, and Complexity 5(1) (2016) 33--42 | DOI:10.5890/DNC.2016.03.005

M.U. Akhmet; M. Karacaören

Department of Mathematics, Middle East Technical University, 06800, Ankara, Turkey

Download Full Text PDF

 

Abstract

In this paper, by using the concept of differential equations with piecewise constant argument, the model of Hopfield neural networks with constant delay is developed. Sufficient conditions for the existence of an equilibrium as well as its global exponential stability by means of Lyapunov functionals and a linear matrix inequality (LMI) are obtained. An example is given to illustrate our results.

References

  1. [1]  Hopfield, J.J.(1984), Neurons with graded response have collective computational properties like those of two-stage neurons, Proc. Nat. Acad. Sci. Biol. 81, 3088-3092.
  2. [2]  Tank, D. and Hopfield, J.J.(1986), Simple neural optimization networks: an A/D converter, signal decision circuit and a linear programming circuit,IEEE Transactions on Circuits and Systems 33, 533-541.
  3. [3]  Zhang, J. and Jin, X. (2000), Global stability analysis in delayed Hopfield neural network models, Neural Networks 13, 745-753.
  4. [4]  Cao, J. (2004), An estimation of the domain of attraction and convergence rate for Hopfield continuous feedback neural networks, Phys. Lett. A 325, 370-374.
  5. [5]  Cao, J.(2000), Estimation of the Domain of Attraction and the Convergence Rate of a Hopfield Associative Memory and an Application, Journal of Computer and System Sciences 60, 179-186.
  6. [6]  Cao, J.D. and Wang, J.(2005), Global exponential stability and periodicity of recurrent neural networks with time delay,IEEE Trans. Circuits and System I 52, 920-931.
  7. [7]  Chua, L.O. and Yang, L.(1988), Cellular neural networks: applications,IEEE Trans. Circuits and Systems 35, 1257- 1272.
  8. [8]  Driver, R.D.(1979), Can the future influence the present? Physical Review D 19, 1098-11071979.
  9. [9]  Baldi,P. and Atiya, A.F. (1994), How Delays Affect Neural Dynamics and Learning, IEEE Transactions on Neural Networks 5(4), 612-621.
  10. [10]  Civalleri, P.P., Gilli, M., and Pandolfi, L. (1993), On the stability of cellular neural networks with delay, IEEE Trans. Circuits and Systems I 40, 157-165.
  11. [11]  Forti, M. and Tesi, A.(1995), New Conditions for global stability of neural networks with application to linear and quadratic programming problems, IEEE Trans. Circuits and Systems I 42, 354-366.
  12. [12]  Gopalsamy, K. (1981) Time lags in Richardson's arms race model, J. Social Biol. Struct. 4, 303-317.
  13. [13]  Gopalsamy, K. (1980), Time lags and global stability in two-species competition, Bulletin of Mathematical Biology 42, 729-737.
  14. [14]  Chua, L.O. and Roska, T. (1992), Cellular neural networks with nonlinear and delay type template elements and nonuniform grids, International Journal of Circuit Theory and Applications 20, 449-451.
  15. [15]  Marcus, C.M. andWestervelt, R.M. (1989), Stability of analog neural networks with delay, Phys. Rev. A 39, 347.
  16. [16]  Liao, X.F., Wu, Z.F., Yu, J.B. (2002), Stability analysis for cellular neural networks with continuous delay,J. Comput. Appl. Math. 143, 29-47.
  17. [17]  Peng, J., Qiao, H., and Xu, Z. (2002), A new approach to stability of neural networks with time varying delays, Neural network 15, 95-103.
  18. [18]  Ren, F. and Cao, J. (2006), LMI-based criteria for stability of high order neural networks with time varying delays, Nonlinear analysis Real World Applications 7, 967-979.
  19. [19]  Zhou, D. and Cao, J.(2002), Globally exponential stability conditions for cellular neural networks with time-varying delays, Applied Mathematics and Computation 13, 487-496.
  20. [20]  Xu, S. and Lam, J.(2006), A new approach to exponential stability of neural networkswith time-varying delays, Neural networks 19, 76-83.
  21. [21]  Song, Q. and Cao, J. (2006), Stability analysis of Cohen-Grossberg neural network with both time-varying and continuously distributed delays. J. Comput. Appl. Math. 197, 188-203.
  22. [22]  Cooke, K.L. andWiener, J. (1984), Retarded differential equations with piecewise constant delays, J.Math. Anal. Appl. 99, 265-297.
  23. [23]  Shah, S.M. and Wiener, J.(1983), Advanced differential equations with piecewise constant argument deviations,Int. J. Math. Sci. 6, 671-703.
  24. [24]  Wiener, J. (1984), Pointwise initial value problems for functional-differential equations, Differential Equations, North- Holland Mathematics Studies 92, 571-580.
  25. [25]  Akhmet, M.U. (2006), On the integral manifolds of the differential equations with piecewise constant argument of generalized type, In R. P. Agarval, K. Perera (Eds.), Proceedings of the conference on differential and difference equations at the Florida Institute of Technology (pp. 11-20). Hindawi Publishing Corporation.
  26. [26]  Akhmet, M.U. (2007), On the reduction principle for differential equations with piecewise constant argument of generalized type, Journal of Mathematical Analysis and Applications 336, 646-663.
  27. [27]  Akhmet, M.U. (2008), Almost periodic solutions of differential equations with a piecewise constant argument of generalized type,Nonlinear Analysis: Hybrid Systems 2, 456-457.
  28. [28]  Akhmet, M.U. (2007), Integral manifolds of differential equations with piecewise constant argument of generalized type, Nonlinear Analysis 66, 367-383.
  29. [29]  Akhmet, M.U. (2008), Stability of differential equations with a piecewise constant argument of generalized type, Nonlinear Analysis 68, 794-803.
  30. [30]  Akhmet, M.U. and Aruğaslan, D. (2009), Lyapunov-Razumikhin method for differential equations with piecewise constant argument,Discrete and Continuous Dynamical Systems 25(2), 457-466
  31. [31]  Akhmet, M.U., Aruğaslan, D., and Yılmaz, E. (2010), Stability in cellular neural networks with a piecewise constant argument, J. Comput. Appl. Math. 233, 2365-2373.
  32. [32]  Akhmet, M.U., Aruğaslan, D., and Yılmaz, E. (2010), Stability analysis of recurrent neural networks with piecewise constant argument of generalized type, Neural Networks 23, 305-311
  33. [33]  Akhmet, M.U. (2011),Nonlinear Hybrid Continuous/Discrete-Time Models, Atlantis Press, Amsterdam-Paris.
  34. [34]  Akhmet, M.U., Aruğaslan, D., and Yılmaz, E. (2011), Method of Lyapunov functions for differential equations with piecewise constant delay, J. Comput. Appl. Math. 235, 4554-4560.
  35. [35]  Akhmet, M.U. and Yılmaz, E. (2014), Neural Networks with Discontinuous/Impact Activations, New York, USA, Springer
  36. [36]  Gopalsamy X.Z. He, (1994), Stability in asymmetric Hopfield nets with transmission delays, Phys. D 76(4), 344-358.
  37. [37]  Ye, H., Michel, A. N., and Wang K.N.(1995), Qualitative analysis of Cohen Grossberg neural Networks with multiple delays, Phys. Rev E 51, 2611-2618.
  38. [38]  Xu, Z.B.(1995), Global convergence and asymptotic stability of asymmetric Hopfield neural networks, J. Math. Anal. Appl. 191, 405-427.
  39. [39]  Cao, J. (2001), Global exponential stability of Hopfield neural networks,Internat. J. Systems Sci. 32, 233-236.
  40. [40]  Zhang, J.Y. and Jin, X.S.(2000), Global stability analysis in delayed Hopfield neural network models, Neural Networks 13, 745-753.
  41. [41]  Cui, B.T. and Lou, X.Y. (2006), Global asymptotic stability of BAM neural networks with distributed delays and reaction diffusion terms,Chaos Solutions Fractals 27(5), 1347-1354.
  42. [42]  Lou, X.Y. and Cui, B.T. (2006), Global asymptotic stability of delay BAM neural networks with impulses, Chaos Solutions Fractals 29(4), 1023-1031.
  43. [43]  Xu, B.J., Liu, X.Z., and Liao, X.X.(2003), Global asymptotic stability of high-order Hopfield type neural networks with time delays,Comput. Math. Appl. 45, 1729-1737.
  44. [44]  Cao, J., Liang, J., and Lam, J. (2004), Exponential stability of high-order bidirectional associative memory neural networks with time delays, Phys. D 199, 425-436.
  45. [45]  Liao, X., Chen, G.R., and Sanchenz, E.N. (2002), Delay dependent exponential stability analysis of delayed neural networks: An LMI approach,Neural Networks 15, 855-866.
  46. [46]  Ren, F. and Cao, J. (2006), LMI-based criteria for stability of high-order neural networks with time-varying delay, Nonlinear Anal. Ser. B 7(5), 967-979.
  47. [47]  Cao, J., Li, X.(2005), Stability in delayed Cohen-Grossberg neural networks: LMI optimization approach, Phys. D 212(1- 2), 54-65.
  48. [48]  Cao, J. and Wang, J. (2005), Global asymptotic and robust stability of recurrent neural networks with time delays, IEEE Trans. Circuits Syst. I 52(2), 417-426.
  49. [49]  Cao, J. and Song, Q.(2006), Stability in Cohen-Grossberg type BAM neural networks with time-varying delays, Nonlinearity 19(7), 1601-1617.
  50. [50]  Xu, S. and Lam, J.(2006), A new approach to exponential stability analysis of neural networks with time-varying delays, Neural Networks 19, 76-83.
  51. [51]  Mohamad, S., Gopalsamy, K., and Akc?a, H. (2008), Exponential stability of artificial neural networks with distributed delays and large impulses, Nonlinear Analysis: Real World Applications 9, 872-888.
  52. [52]  Zhang, Q., Wei, X.P., and Xu, J.(2003), Global asymptotic stability of Hopfield neural networks with transmission delays, Phys. Lett. A 318, 399-405.
  53. [53]  Coombes, S. and Laing, C. (2009), Delays in activity-based neural networks, Philosophical Transactions of the Royal Society London, Series A (Mathematical, Physical and Engineering Sciences) 367, 1117-1129.
  54. [54]  Boyd, S. et al. (1994), Linear Matrix Inequalities in System and Control Theory, SIAM, Philadelphia.