Neural Processing Letters

, Volume 50, Issue 3, pp 2797–2819 | Cite as

Exponential Stabilization for Hybrid Recurrent Neural Networks by Delayed Noises Rooted in Discrete Observations of State and Mode

  • Lichao Feng
  • Jinde CaoEmail author
  • Jun Hu
  • Zhihui Wu
  • Leszek Rutkowski


Recently, the random noises derived from discrete state observations are creatively designed to realize the role of stabilization for deterministic systems in the existing result. However, for a hybrid neural network, except for the factor of discrete state observations, one always needs to consider the factors of delays and discrete mode identifications. Hence, taking delays and discrete mode identifications into account for random noises is more reasonable and practical than the original work. Motivated by the idea above, this brief is to design delayed random noises derived from discrete state observations and discrete mode identifications to almost surely exponentially stabilize an unstable hybrid recurrent neural networks, by virtue of M-matrix and stochastic analysis methods.


Hybrid recurrent neural networks Random noises Exponential stabilization Discrete observations Delay 



This project is partially supported by National Natural Science Foundation of China (Nos. 11571024, 61833005, 61573096 and 61272530), China Postdoctoral Science Foundation (No. 2017M621588), Science and Technology Research Foundation of Higher Education Institutions of Hebei Province of China (No. QN2017116), Graduate Foundation of North China University of Science and Technology (No. J1905), and by the Polish National Science Centre (No. 2017/27/B/ST6/02852).


  1. 1.
    Hopfield JJ (1982) Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci 79(8):2554–2558MathSciNetzbMATHGoogle Scholar
  2. 2.
    Huang C, Zhang H (2019) Periodicity of non-autonomous inertial neural networks involving proportional delays and non-reduced order method. Int J Biomath 12(2):1950016MathSciNetzbMATHGoogle Scholar
  3. 3.
    Cao J, Wang J (2005) Global asymptotic and robust stability of recurrent neural networks with time delays. IEEE Trans Circuits Syst I: Regul Pap 52(2):417–426MathSciNetzbMATHGoogle Scholar
  4. 4.
    Cao J, Yuan K, Li H (2006) Global asymptotical stability of recurrent neural networks with multiple discrete delays and distributed delays. IEEE Trans Neural Netw 17(6):1646–1651Google Scholar
  5. 5.
    Huang C, Yang Z, Yi T, Zou X (2014) On the basins of attraction for a class of delay differential equations with non-monotone bistable nonlinearities. J Differ Equ 256(7):2101–2114MathSciNetzbMATHGoogle Scholar
  6. 6.
    Li R, Cao J, Alsaedi A et al (2017) Exponential and fixed-time synchronization of Cohen–Grossberg neural networks with time-varying delays and reaction–diffusion terms. Appl Math Comput 313:37–51MathSciNetzbMATHGoogle Scholar
  7. 7.
    Huang H, Huang T, Chen X et al (2013) Exponential stabilization of delayed recurrent neural networks: a state estimation based approach. Neural Netw 48:153–157zbMATHGoogle Scholar
  8. 8.
    Huang C, Cao J, Cao J (2016) Stability analysis of switched cellular neural networks: a mode-dependent average dwell time approach. Neural Netw 82:84–99Google Scholar
  9. 9.
    Huang C, Liu B (2019) New studies on dynamic analysis of inertial neural networks involving non-reduced order method. Neurocomputing 325:283–287Google Scholar
  10. 10.
    Duan L, Wei H, Huang L (2019) Finite-time synchronization of delayed fuzzy cellular neural networks with discontinuous activations. Fuzzy Sets Syst 361:56–70MathSciNetzbMATHGoogle Scholar
  11. 11.
    Duan L, Shi M, Wang Z et al (2019) Global exponential synchronization of delayed complex-valued recurrent neural networks with discontinuous activations. Neural Process Lett. CrossRefGoogle Scholar
  12. 12.
    Xu C, Yang X, Lu J et al (2018) Finite-time synchronization of networks via quantized intermittent pinning control. IEEE Trans Cybern 48(10):3021–3027Google Scholar
  13. 13.
    Huang C, Cao J, Wen F, Yang X (2016) Stability Analysis of SIR Model with Distributed Delay on Complex Networks. Plos One 11(8):e0158813Google Scholar
  14. 14.
    Huang C, Liu B, Tian X et al (2019) Global convergence on asymptotically almost periodic SICNNs with nonlinear decay functions. Neural Process Lett 49(2):625–641Google Scholar
  15. 15.
    Huang C, Cao J (2011) Convergence dynamics of stochastic Cohen-Grossberg neural networks with unbounded distributed delays. IEEE Trans Neural Netw 22(4):561–572Google Scholar
  16. 16.
    Khasminskii RZ (1981) Stochastic stability of differential equations. Sijthoff and Noordhoff, Alphen aan den RijnGoogle Scholar
  17. 17.
    Arnold L, Crauel H, Wihstutz V (1983) Stabilization of linear systems by noise. SIAM J Control Optim 21(3):451–461MathSciNetzbMATHGoogle Scholar
  18. 18.
    Mao X, Marion G, Renshaw E (2002) Environmental noise suppresses explosion in population dynamics. Stoch Process Appl 97:95–110MathSciNetzbMATHGoogle Scholar
  19. 19.
    Mao X (2007) Stochastic differential equations and applications, 2nd edn. Horwood Publishing, ChichesterzbMATHGoogle Scholar
  20. 20.
    Mao X (2007) Stability and stabilisation of stochastic differential delay equations. IET Control Theory Appl 1(6):1551–1566Google Scholar
  21. 21.
    Appleby JAD, Mao X, Rodkina A (2008) Stabilization and destabilization of nonlinear differential equations by noise. IEEE Trans Autom Control 53(3):683–691MathSciNetzbMATHGoogle Scholar
  22. 22.
    Deng F, Luo Q, Mao X et al (2008) Noise suppress or expresss exponential growth. Syst Control Lett 57:262–270Google Scholar
  23. 23.
    Wu F, Hu S (2011) Stochastic suppression and stabilization of delay differential systems. Int J Robust Nonlinear Control 21:488–500MathSciNetzbMATHGoogle Scholar
  24. 24.
    Liu L, Shen Y (2012) Noise suppresses explosive solutions of differential systems with coefficients satisfying the polynomial growth condition. Automatica 48(4):619–624MathSciNetzbMATHGoogle Scholar
  25. 25.
    Song S, Zhu Q (2015) Noise suppresses explosive solutions of differential systems: a new general polynomial growth condition. J Math Anal Appl 431(1):648–661MathSciNetzbMATHGoogle Scholar
  26. 26.
    Guo Q, Mao X, Yue R (2016) Almost sure exponential stability of stochastic differential delay equations. SIAM J Control Optim 54(4):1919–1933MathSciNetzbMATHGoogle Scholar
  27. 27.
    Zhu S, Yang Q, Shen Y (2016) Noise further expresses exponential decay for globally exponentially stable time-varying delayed neural networks. Neural Netw 77:7–13zbMATHGoogle Scholar
  28. 28.
    Feng L, Wu Z, Zheng S (2018) A note on explosion suppression for nonlinear delay differential systems by polynomial noise. Int J Gen Syst 47(2):137–154MathSciNetGoogle Scholar
  29. 29.
    Feng L, Li S, Song R et al (2018) Suppression of explosion by polynomial noise for nonlinear differential systems. Sci China Inf Sci 61(7):070215MathSciNetGoogle Scholar
  30. 30.
    Hu J, Wang Z, Alsaadi FE et al (2017) Event-based filtering for time-varying nonlinear systems subject to multiple missing measurements with uncertain missing probabilities. Inf Fus 38:74–83Google Scholar
  31. 31.
    Hu J, Wang Z, Gao H (2018) Joint state and fault estimation for uncertain time-varying nonlinear systems with randomly occurring faults and sensor saturations. Automatica 97:150–160MathSciNetzbMATHGoogle Scholar
  32. 32.
    Zhang H, Hu J, Liu H et al (2019) Recursive state estimation for time-varying complex networks subject to missing measurements and stochastic inner coupling under random access protocol. Neurocomputing 346:48–57Google Scholar
  33. 33.
    Mao X (2016) Almost sure exponential stabilization by discrete-time stochastic feedback control. IEEE Trans Autom Control 61(6):1619–1624MathSciNetzbMATHGoogle Scholar
  34. 34.
    Liberzon D (2003) Switching in systems and control. Birkhauser, BostonzbMATHGoogle Scholar
  35. 35.
    Shen Y, Wang J (2009) Almost sure exponential stability of recurrent neural networks with Markovian switching. IEEE Trans Neural Netw 20(5):840–855Google Scholar
  36. 36.
    Huang H, Huang T, Chen X (2012) Global exponential estimates of delayed stochastic neural networks with Markovian switching. Neural Netw 36:136–145zbMATHGoogle Scholar
  37. 37.
    Mathiyalagan K, Su H, Shi P et al (2015) Exponential \(H_{\infty }\) filtering for discrete-time switched neural networks with random delays. IEEE Trans Cybern 45(4):676–687Google Scholar
  38. 38.
    Shen H, Zhu Y, Zhang L et al (2017) Extended dissipative state estimation for Markov jump neural networks with unreliable links. IEEE Trans Neural Netw Learn Syst 28(2):346–358MathSciNetGoogle Scholar
  39. 39.
    Liu L, Cao J, Qian C (2018) pth moment exponential input-to-state stability of delayed recurrent neural networks with Markovian switching via vector Lyapunov function. IEEE Trans Neural Netw Learn Syst 29(7):3152–3163MathSciNetGoogle Scholar
  40. 40.
    Yang X, Lu J, Ho DWC et al (2018) Synchronization of uncertain hybrid switching and impulsive complex networks. Appl Math Model 59:379–392MathSciNetGoogle Scholar
  41. 41.
    Yang X, Song Q, Cao J et al (2019) Synchronization of coupled Markovian reaction-diffusion neural networks with proportional delays via quantized control. IEEE Trans Neural Netw Learn Syst 3(3):951–958MathSciNetGoogle Scholar
  42. 42.
    Mao X, Yuan C (2006) Stochastic differential equations with Markovian switching. Imperial College Press, LondonzbMATHGoogle Scholar
  43. 43.
    Mao X, Yin G, Yuan C (2007) Stabilization and destabilization of hybrid systems of stochastic differential equations. Automatica 43(2):264–273MathSciNetzbMATHGoogle Scholar
  44. 44.
    Shen Y, Wang J (2007) Noise-induced stabilization of the recurrent neural networks with mixed time-varying delays and Markovian-switching parameters. IEEE Trans Neural Netw 18(6):1857–1862Google Scholar
  45. 45.
    Hu G, Liu M, Mao X et al (2009) Noise suppresses exponential growth under regime switching. J Math Anal Appl 355(2):783–795MathSciNetzbMATHGoogle Scholar
  46. 46.
    Zhu S, Shen Y, Chen G (2010) Noise suppress or express exponential growth for hybrid Hopfield neural networks. Phys Lett A 374(19):2035–2043zbMATHGoogle Scholar
  47. 47.
    Zhu S, Shen Y, Chen G (2012) Noise suppress exponential growth for hybrid Hopfield neural networks. Math Comput Simul 86:10–20MathSciNetGoogle Scholar
  48. 48.
    Yin R, Wu F, Shen Y (2012) The asymptotic properties of the suppressed system by Brownian noise. Int J Control 85(8):1112–1120MathSciNetzbMATHGoogle Scholar
  49. 49.
    Yin R, Zhu Q, Shen Y et al (2016) The asymptotic properties of the suppressed functional differential system by Brownian noise under regime switching. Int J Control 89(11):2227–2239MathSciNetzbMATHGoogle Scholar
  50. 50.
    Zhu S, Sun K, Zhou S et al (2017) Stochastic suppression and almost surely stabilization of non-autonomous hybrid system with a new general one-sided polynomial growth condition. J Frankl Inst 354(15):6550–6566MathSciNetzbMATHGoogle Scholar
  51. 51.
    Yin G, Liu R, Zhang Q (2002) Recursive algorithms for stock liquidation: a stochastic optimization approach. SIAM J Optim 13(1):240–263MathSciNetzbMATHGoogle Scholar
  52. 52.
    Krishnamurthy V, Wang X, Yin G (2004) Spreading code optimization and adaptation in CDMA via discrete stochastic approximation. IEEE Trans Inf Theory 50(9):1927–1949MathSciNetzbMATHGoogle Scholar
  53. 53.
    Zhu Q, Zhang Q (2017) pth moment exponential stabilisation of hybrid stochastic differential equations by feedback controls based on discrete-time state observations with a time delay. IET Control Theory Appl 11(12):1992–2003MathSciNetGoogle Scholar
  54. 54.
    Feng L, Cao J, Liu L (2019) Robust analysis of discrete time noises for stochastic systems and application in neural networks. Int J Control. CrossRefGoogle Scholar
  55. 55.
    Feng L, Cao J, Liu L (2019) Stability analysis in a class of Markov switched stochastic Hopfield neural networks. Neural Process Lett. CrossRefGoogle Scholar
  56. 56.
    Feng L, Cao J, Liu L et al (2019) Asymptotic stability of nonlinear hybrid stochastic systems driven by linear discrete time noises. Nonlinear Anal Hybrid Syst 33:336–352MathSciNetGoogle Scholar
  57. 57.
    Song M, Mao X (2018) Almost sure exponential stability of hybrid stochastic functional differential equations. J Math Anal Appl 458(2):1390–1408MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.College of ScienceNorth China University of Science and TechnologyTangshanChina
  2. 2.The Jiangsu Provincial Key Laboratory of Networked Collective Intelligence, and School of MathematicsSoutheast UniversityNanjingChina
  3. 3.Department of MathematicsHarbin University of Science and TechnologyHarbinChina
  4. 4.Institute of Computational IntelligenceCzestochowa University of TechnologyCzestochowaPoland

Personalised recommendations