Skip to main content
SpringerLink
Log in

Passivity Analysis of Delayed Neural Networks with Discontinuous Activations

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

In this paper, we investigate the passivity problem of delayed neural networks, where the activation functions are discontinuous. Based on differential inclusion theory, sufficient conditions for this problem are obtained by means of generalized Lyapunov approach. The theoretical results can be checked by solving some linear matrix inequalities. The results extend previous researches on the passivity of delayed neural networks.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Kaslik E, Sivasundaram S (2011) Impulsive hybrid discrete-time Hopfield neural networks with delays and multistability analysis. Neural Netw 24:370–377

    Article  Google Scholar 

  2. Yang YQ, Cao JD (2008) A feedback neural network for solving convex constraint optimization problems. Appl Math Comput 201:340–350

    Article  Google Scholar 

  3. Shen Y, Wang J (2009) Almost sure exponential stability of recurrent neural networks with markovian switching. IEEE Trans Neural Netw 20:840–855

    Article  Google Scholar 

  4. Liu YR, Wang ZD, Liang JL, Liu XH (2009) Stability and synchronization of discrete-time markovian jumping neural networks with mixed mode-dependent time delays. IEEE Trans Neural Netw 20:1102–1116

    Article  Google Scholar 

  5. Liu ZW, Zhang HG, Zhang QL (2010) Novel stability analysis for recurrent neural networks with multiple delays via line integral-type L-K functional. IEEE Trans Neural Netw 21:1710–1718

    Article  Google Scholar 

  6. Xia Y, Wang J (2004) A general projection neural network for solving monotone variational inequalities and related optimization problems. IEEE Trans Neural Netw 15:318–328

    Article  Google Scholar 

  7. Yang XS (2009) Existence and global exponential stability of periodic solution for Cohen-Grossberg shunting inhibitory cellular neural networks with delays and impulses. Neurocomputing 72:2219–2226

    Article  Google Scholar 

  8. Liu ZW, Huang GB, Wang ZS (2010) Novel Weighting-delay-based stability criteria for recurrent neural networks with time-varying delay. IEEE Trans Neural Netw 21:91–106

    Article  Google Scholar 

  9. Zhang HG, Quan YB (2001) Modeling identification and control of a class of nonlinear system. IEEE Trans Fuzzy Syst 9:349–354

    Article  Google Scholar 

  10. Huang H, Ho DWC, Lam J (2005) Stochastic stability analysis of fuzzy Hopfield neural networks with time-varying delays. IEEE Trans Circ Sys II Exp Briefs 52:251–255

    Article  Google Scholar 

  11. Liu ZW, Zhang HG, Wang ZS (2009) Novel stability criterions of a new fuzzy cellular neural networks with time-varying delays. Neurocomputing 72:1056–1064

    Article  Google Scholar 

  12. Wang LL, Chen TP (2012) Complete stability of cellular neural networks with unbounded time-varying delays. Neural Netw 36:11–17

    Article  Google Scholar 

  13. Qiu JL (2010) Dynamics of high-order Hopfield neural networks with time delays. Neurocomputing 73:820–826

    Article  Google Scholar 

  14. Zhang L, Zhang Y, Yu JL (2008) Multiperiodicity and attractivity of delayed recurrent neural networks with unsaturating piecewise linear transfer functions. IEEE Trans Neural Netw 19:158–167

    Article  Google Scholar 

  15. Hopfield JJ (1984) Neurons with graded response have collective computational properties like those of two-state neurons. Proc Natl Acad Sci 81:3088–3092

    Article  Google Scholar 

  16. Forti M, Nistri P (2003) Global convergence of neural networks with discontinuous neuron activation. IEEE Trans Circ Sys I 50:1421–1435

    Article  Google Scholar 

  17. Forti M, Nistri P, Papini D (2005) Global exponential stability and global convergence in finite time of delayed neural networks with infinite gain. IEEE Trans Neural Netw 16:1449–1463

    Article  Google Scholar 

  18. Forti M, Grazzini M, Nistri P (2006) Generalized Lyapunov approach for convergence of neural networks with discontinuous or non-Lipchitz activations. Physica D 214:88–99

    Article  Google Scholar 

  19. Forti M (2007) M-matrices and global convergence of discontinuous neural networks. Int J Circ Theory Appl 35:105–130

    Article  Google Scholar 

  20. Allegretto W, Papini D, Forti M (2010) Common asymptotic behavior of solutions and almost periodicity for discontinuous, delayed, and impulsive neural networks. IEEE Trans Neural Netw 21:1110–1125

    Article  Google Scholar 

  21. Lu WL, Chen TP (2005) Dynamical behaviors of Cohen-Grossberg neural networks with discontinuous activation functions. Neural Netw 18:231–242

    Article  Google Scholar 

  22. Liu WL, Chen TP (2008) Almost periodic dynamics of a class of delayed neural networks with discontinuous activations. Neural Comput 20:1065–1090

    Article  Google Scholar 

  23. Wang JF, Huang LH, Guo ZY (2009) Global asymptotic stability of neural networks with discontinuous activations. Neural Netw 22:931–937

    Article  Google Scholar 

  24. Cai ZW, Huang LH, Guo ZY, Chen XY (2012) On the periodic dynamics of a class of time-varying delayed neural networks via differential inclusions. Neural Netw 33:97–113

    Article  Google Scholar 

  25. Liu XY, Cao JD (2010) Robust state estimation for neural networks with discontinuous activations. IEEE Trans Sys Man Cybern Part B Cybern 40:1425–1437

    Article  Google Scholar 

  26. Nie XB, Cao JD (2012) Existence and global stability of equilibrium point for delayed competitive neural networks with discontinuous activation functions. Int J Sys Sci 43:459–474

    Article  Google Scholar 

  27. Zuo Y, Wang Y, Huang L, Wang Z, Liu X, Li C (2009) Robust stability criterion for delayed neural networks with discontinuous activation functions. Neural Process Lett 29:29–44

    Article  Google Scholar 

  28. Ahn CK (2012) Switched exponential state estimation of neural networks based on passivity theory. Nonlinear Dyn 67:573–586

    Article  Google Scholar 

  29. Haddad WM, Bailey JM, Hovakimyan N (2005) Passivity-based neural network adaptive output feedback control for nonlinear nonnegative dynamical systems. IEEE Trans Neural Netw 16:387–398

    Article  Google Scholar 

  30. Zhang ZX, Mou SS, Lam J, Gao HJ (2009) New passivity criteria for neural networks with time-varying delay. Neural Netw 22:864–868

    Article  Google Scholar 

  31. Xu SY, Zheng WX, Zou Y (2009) Passivity analysis of neural networks with time-varying delays. IEEE Trans Circ Sys II Exp Briefs 56:325–329

    Article  Google Scholar 

  32. Zhu S, Shen Y, Chen GC (2010) Exponential passivity of neural networks with time-varying delay and uncertainty. Phys Lett A 375:136–142

    Article  Google Scholar 

  33. Ahn CK (2010) Passive learning and input-to-state stability of switched Hopfield neural networks with time-delay. Inf Sci 180:4582–4594

    Article  Google Scholar 

  34. Song OK, Cao JD (2012) Passivity of uncertain neural networks with both leakage delay and time-varying delay. Nonlinear Dyn 67:1695–1707

    Article  Google Scholar 

  35. Ahn CK (2011) Some new results on stability of Takagi–Sugeno fuzzy Hopfield neural networks. Fuzzy Sets Sys 179:100–111

    Article  Google Scholar 

  36. Ahn CK (2013) State estimation for T-S fuzzy Hopfield neural networks via strict putput passivation of the error system. Int J Gen Sys 42:503–518

    Article  Google Scholar 

  37. Ahn CK (2012) An error passivation approach to filtering fo switched neural networks with noise disturbance. Neural Comput Appl 21:853–861

    Article  Google Scholar 

  38. Ahn CK (2013) Passive and exponential filter design for fuzzy neural networks. Inf Sci 238:126–137

    Article  Google Scholar 

  39. Liu J, Liu XZ, Xie WC (2013) Global convengence of neural networks with mixed time-varying delays and discontinuous neuron activations. Inf Sci 183:92–105

    Article  Google Scholar 

  40. Roska T, Chua LO (1992) Cellular neural networks with nonlinear and delay-type template. Int L Circ Theory Appl 20:469–481

    Article  Google Scholar 

  41. Li F (2010) Delayed Lagrangian neural networks for solving convex programming problems. Neurocomputing 73:2266–2273

    Article  Google Scholar 

  42. Hosseini A, Wang J, Hosseini M (2013) A recurrent neural network for solving a class of generalized convex optimization problems. Neural Netw 44:78–85

    Article  Google Scholar 

  43. Guo ZS, Liu QS, Wang J (2011) A one-layer recurrent neural network for pseudoconvex optimization subject to linear equality constraints. IEEE Trans Neural Netw 22:1892–1900

    Article  Google Scholar 

  44. Bao G, Zeng ZG (2012) Analysis and design of associative memories based on recurrent neural network with discontinuous activation functions. Neurocomputing 77:101–107

    Article  Google Scholar 

Download references

Acknowledgments

The work is supported by the Natural Science Foundation of China under Grants 60974021 and 61125303, the 973 Program of China under Grant 2011CB710606 and the Fund for Distinguished Young Scholars of Hubei Province under Grant 2010CDA081.

Author information

Authors and Affiliations

  1. Department of Control Science and Engineering, Huazhong University of Science and Technology, Wuhan, 430074, China

    Jian Xiao, Zhigang Zeng & Wenwen Shen

  2. Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China, Wuhan, 430074 , China

    Jian Xiao, Zhigang Zeng & Wenwen Shen

Authors
  1. Jian Xiao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhigang Zeng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wenwen Shen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jian Xiao.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xiao, J., Zeng, Z. & Shen, W. Passivity Analysis of Delayed Neural Networks with Discontinuous Activations. Neural Process Lett 42, 215–232 (2015). https://doi.org/10.1007/s11063-014-9353-x

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-014-9353-x

Keywords

Search

Navigation