Hybrid Impulsive Neural Networks with Interval-Uncertain Weights

  • Zhi-Hong Guan
  • Bin Hu
  • Xuemin (Sherman) Shen


Neural networks have emerged as a powerful illustrative diagram for the brain. Unveiling the mechanism of neural-dynamic evolution is one of the crucial steps toward understanding how the brain works and evolves. Inspired by the universal existence of impulses in many real systems, this chapter introduces a class of hybrid neural networks with impulses, time-delays and interval uncertainties, and studies its global dynamic evolution by robust interval analysis. The hybrid neural networks incorporate both continuous-time implementation and impulsive jump in mutual activations, where time-delays and interval uncertainties are represented simultaneously. By constructing a Banach contraction mapping, the existence and uniqueness of the equilibrium of the hybrid neural network model are proved and analyzed in detail. Based on nonsmooth Lyapunov functions and delayed impulsive differential equations, new criteria are derived for ensuring the global robust exponential stability of the hybrid neural networks. Convergence analysis together with illustrative examples show the effectiveness of the theoretical results.


  1. 1.
    J. Hopfield, “Neural networks and physical systems with emergent collective computational abilities,” Proc. Natl Acad. Sci., vol. 79, no. 8, pp. 2554–2558, 1982.MathSciNetzbMATHGoogle Scholar
  2. 2.
    C. Li, X. Yu, T. Huang, G. Chen, and X. He, “A generalized hopfield network for nonsmooth constrained convex optimization: Lie derivative approach,” IEEE Trans. Neural Netw. Learn. Syst., vol. 27, no. 2, pp. 308–321, 2016.MathSciNetGoogle Scholar
  3. 3.
    P. Baldi and A. F. Atiya, “How delays affect neural dynamics and learning,” IEEE Trans. Neural Netw., vol. 5, no. 4, pp. 612–621, 1994.Google Scholar
  4. 4.
    Z.-H. Guan and G. Chen, “On delayed impulsive Hopfield neural networks,” Neural Netw., vol. 12, no. 2, pp. 273–280, 1999.Google Scholar
  5. 5.
    W. Lu and T. Chen, “Synchronization of coupled connected neural networks with delays,” IEEE Trans. Circuits Syst. I, vol. 51, no. 12, pp. 2491–2503, 2004.MathSciNetzbMATHGoogle Scholar
  6. 6.
    M. A. Cohen and S. Grossberg, “Absolute stability of global pattern formation and parallel memory storage by competitive neural networks,” IEEE Trans. on Sys. Man and Cybern., vol. 13, no. 5, pp. 815–826, 1983.MathSciNetzbMATHGoogle Scholar
  7. 7.
    K. Gopalsamy and X.-Z. He, “Delay-independent stability in bidirectional associative memory networks,” IEEE Trans. on Neural netw., vol. 5, no. 6, pp. 998–1002, 1994.Google Scholar
  8. 8.
    Y. He, G. Liu, D. Rees, and M. Wu, “Stability analysis for neural networks with time-varying interval delay,” IEEE Trans. Neural Netw., vol. 18, no. 6, pp. 1850–1854, 2007.Google Scholar
  9. 9.
    S. Duan, H. Wang, L. Wang, T. Huang, and C. Li, “Impulsive effects and stability analysis on memristive neural networks with variable delays,” IEEE Trans. Neural Netw. Learn. Syst., vol. 28, no. 2, pp. 476–481, 2017.Google Scholar
  10. 10.
    X. Yang and D. W. C. Ho, “Synchronization of delayed memristive neural networks: robust analysis approach,” IEEE Trans. Cybern., vol. 46, no. 12, pp. 3377–3387, 2016.Google Scholar
  11. 11.
    W. Zhang, C. Li, T. Huang, and X. He, “Synchronization of memristor-based coupling recurrent neural networks with time-varying delays and impulses,” IEEE Trans. Neural Netw. Learn. Syst., vol. 26, no. 12, pp. 3308–3313, 2015.MathSciNetGoogle Scholar
  12. 12.
    T. Shiraishi, S. Matsuyama, and H. Kitano, “Large-scale analysis of network bistability for human cancers,” PLoS Computaional Biology, vol. 7, no. 7, pp. e1000851, 2010.Google Scholar
  13. 13.
    M. Forti and P. Nistri, “Global convergence of neural networks with discontinuous neuron activations,” IEEE Trans. Circuits Syst. I, vol. 50, no. 11, pp. 1421–1435, 2003.MathSciNetzbMATHGoogle Scholar
  14. 14.
    P. P. Civalleri, M. Gilli, and L. Pandolfi, “On stability of cellular neural networks with delay,” IEEE Trans. Circuits Syst. I, vol. 40, no. 3, pp. 157–164, 1993.MathSciNetzbMATHGoogle Scholar
  15. 15.
    Z.-H. Guan, Y.-Q. Liu, and X.-C. Wen, “Decentralized stabilization of singular and time-delay large-scale control systems with impulsive solutions,” IEEE Trans. Autom. Contr., vol. 40, no. 8, pp. 1437–1441, 1995.MathSciNetzbMATHGoogle Scholar
  16. 16.
    Z.-H. Guan, J. Lam, and G. Chen, “On impulsive autoassociative neural networks,” Neural Netw., vol. 13, no. 1, pp. 63–69, 2000.Google Scholar
  17. 17.
    A. Guez, V. Protopopsecu, and J. Barhen, “On the stability, storage capacity and design of nonlinear continuous neural networks,” IEEE Trans. Syst. Man Cybern., vol. 18, no. 1, pp. 80–87, 1988.Google Scholar
  18. 18.
    C. Hou and J. Qian, “Stability analysis for neural dynamics with time-varying delays,” IEEE Trans. Neural Netw., vol. 9, no. 1, pp. 221–223, 1998.MathSciNetGoogle Scholar
  19. 19.
    X. Liao and J. Yu, “Robust stability for interval Hopfield neural networks with time delay,” IEEE Trans. Neural Netw., vol. 9, no. 5, pp. 1042–1045, 1998.Google Scholar
  20. 20.
    H. Lu, “On stability of nonlinear continuous-time neural networks with delay,” Neural Netw., vol. 13, no. 19, pp. 1135–1144, 2000.Google Scholar
  21. 21.
    K. Matsuoka, “Stability conditions for nonlinear continuous neural networks with asymmetric connection weights,” Neural Netw., vol. 5, no. 3, pp. 495–499, 1992.Google Scholar
  22. 22.
    A. N. Michel and D. L. Gray, “Analysis and synthesis of neural networks with lower block triangular interconnecting structure,” IEEE Trans. Circuits Syst., vol. 37, no. 10, pp. 1267–1283, 1990.MathSciNetGoogle Scholar
  23. 23.
    H. Qiao, J. Peng, and Z.-B. Xu, “Nonlinear measures: a new approach to exponential stability analysis for Hopfield-type neural networks,” IEEE Trans. Neural Netw., vol. 12, no. 2, pp. 360–370, 2001.Google Scholar
  24. 24.
    Y. Xia and J. Wang, “Global exponential stability of recurrent neural networks for solving optimization and related problems,” IEEE Trans. Neural Netw., vol. 11, no. 4, pp. 1017–1022, 2000.Google Scholar
  25. 25.
    H. Yang and T. S. Dillon, “Exponential stability and oscillation of Hopfield graded response neural network,” IEEE Tran. Neural Netw., vol. 5, no. 5, pp. 719–729, 1994.Google Scholar
  26. 26.
    X. Liu and Q. Wang, “Impulsive stabilization of high-order Hopfield-type neural networks with time-varying delays,” IEEE Trans. Neural Netw., vol. 19, no. 1, pp. 71–79, 2008.Google Scholar
  27. 27.
    H. Akca, R. Alassar, V. Covachev, Z. Covacheva, and E. Al-Zahrani, “Continuous time additive Hopfield-type neural networks with impulses,” J. Math. Anal. Appl., vol. 290, no. 2, pp. 436–451, 2004.MathSciNetzbMATHGoogle Scholar
  28. 28.
    A. M. Stoica and I. Yaesh, “Markovian jump delayed Hopfield networks with multiplicative noise,” Automatica, vol. 44, no. 8, pp. 2157–2162, 2008.MathSciNetzbMATHGoogle Scholar
  29. 29.
    Q. Zhang, X. Wei, and J. Xu, “An improved result for complete stability of delayed cellular neural networks,” Automatica, vol. 41, no. 2, pp. 333–337, 2005.MathSciNetzbMATHGoogle Scholar
  30. 30.
    T. Huang, C. Li, S. Duan, and J. A. Starzyk, “Robust exponential stability of uncertain delayed neural networks with stochastic perturbation and impulse effects,” IEEE Trans. Neural Netw. Learn. Syst., vol. 23, no. 6, pp. 866–875, 2012.Google Scholar
  31. 31.
    X. Yang, J. Cao, and J. Lu, “Stochastic synchronization of complex networks with nonidentical nodes via hybrid adaptive and impulsive control,” IEEE Trans. Circuits Syst. I, vol. 59, no. 2, pp. 371–384, 2012.MathSciNetGoogle Scholar
  32. 32.
    J. P. Hespanha and A. S. Morse, “Stability of switched systems with average dwell-time,” in Proc. 38th IEEE Conf. Decision Contr., 1999, pp. 2655–2660.Google Scholar
  33. 33.
    Z.-H. Guan, B. Hu, M. Chi, D.-X. He, and X.-M. Cheng, “Guaranteed performance consensus in second-order multi-agent systems with hybrid impulsive control,” Automatica, vol. 50, no. 7, pp. 2415–2418, 2014.MathSciNetzbMATHGoogle Scholar
  34. 34.
    K. Gopalsamy, “Stability of artificial neural networks with impulses,” Appl. Math. Comput., vol. 154, no. 3, pp. 783–813, 2004.MathSciNetzbMATHGoogle Scholar
  35. 35.
    S. G. Pandit and S. G. Deo, Differential Systems Involving Impulses, New York: Spring-Verlag, 1982.zbMATHGoogle Scholar
  36. 36.
    D. D. Bainov and P. S. Simeonov, Stability Theory of Differential Equations with Impulse Effects: Theory and Applications, Ellis Horwood: Chichester, 1989.Google Scholar
  37. 37.
    A. Halany, Differential Equations: Stability, Oscillations, Time Logs, New York: Academic Press, 1966.Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Zhi-Hong Guan
    • 1
  • Bin Hu
    • 2
  • Xuemin (Sherman) Shen
    • 3
  1. 1.College of AutomationHuazhong University of Science and TechnologyWuhanChina
  2. 2.Wuhan National Laboratory For OptoelectronicsHuazhong University of Science and TechnologyWuhanChina
  3. 3.Electrical and Computer Engineering DepartmentUniversity of WaterlooWaterlooCanada

Personalised recommendations