Skip to main content
SpringerLink
Log in

\(\mathcal{H}_{\infty }\) weight learning of dynamic neural networks with delay and reaction–diffusion

  • Original Paper
  • Published:
Indian Journal of Physics Aims and scope Submit manuscript

Abstract

In this paper, \(\mathcal{H}_{\infty }\) stabilization of dynamic neural networks with both delay and reaction–diffusion factors is studied. First, a delay-independent condition in the structure of linear matrix inequalities is proposed by virtue of an appropriate Lyapunov functional and several integral formulas. Based on the feasible solution of these inequalities, a weight-learning rule is established for ensuring the \(\mathcal{H}_{\infty }\) stability. Then, a delay-dependent condition and the corresponding weight-learning rule are developed by constructing a more complicated Lyapunov functional and employing the free weight-matrix technique. Finally, an example is given to show the effectiveness of the proposed conditions and weight-learning rules.

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

Similar content being viewed by others

References

  1. M Egmont-Petersen, D de Ridder and H Handels Pattern Recognit. 735 2279 (2002)

  2. O Omidvar and D L Elliott Neural System Control (Amsterdam: Elsevier)) (1997)

    Google Scholar 

  3. A N Michel and J A Farrell IEEE Control Syst. Mag. 10 6 (1990)

    Article  Google Scholar 

  4. Y Takefuji Neural Network Parallel Computing. (Berlin: Springer) (1992)

  5. J C Juang IEEE Trans. Neural Netw. 10 1366 (1999)

  6. H Qiao, J Peng, Z B Xu and B Zhang IEEE Trans. Syst. Man. Cybern. B Cybern 33 925 (2003)

    Article  Google Scholar 

  7. M Nag Indian J. Phys. 94 689 https://doi.org/10.1007/s12648-019-01516-5 (2020)

  8. D Li, L P Chen, J Liu and S Tong IEEE Trans. Neural Netw. Learn. Syst. 30 2625 (2019)

    Article  MathSciNet  Google Scholar 

  9. K Wang, H Ye, Y Wang and S Li Indian J. Phys. 96 1943 https://doi.org/10.1007/s12648-021-02186-y (2022).

  10. A M Stoica and I Yaesh Automatica 44 2157 (2008)

    Article  MathSciNet  Google Scholar 

  11. J Cao and D Zhou Neural Netw. 11 1601 (1998)

    Article  Google Scholar 

  12. S Senan, M Ali, R Vadivel and S Arik Neural Netw. 86 32 (2017)

    Article  Google Scholar 

  13. O Faydasicok Neural Netw. 129 288 (2020)

  14. X Liu, K Wu, X Ding and W Zhang IEEE Trans. Neural Netw. Learn. Syst. 33 3227 (2021)

    Article  Google Scholar 

  15. J Cheng, J H Park, J Cao and W Qi IEEE Trans .Cybern. 50 1900 (2020)

    Article  Google Scholar 

  16. Y Chen, X Zhang and Y Xue Math. Comput. Simul. 193 173 (2022)

    Article  Google Scholar 

  17. Z Chen and D Yang Int. J. Control 95 11 (2022)

    Article  Google Scholar 

  18. S H Lee, M J Park, D H Ji and O M Kwon Neural Netw. 146 141 (2022)

    Article  Google Scholar 

  19. P Wang, X Li, N Wang, Y Li, K Shi and J Lu Fuzzy Sets Syst. 426 46 (2022)

    Article  Google Scholar 

  20. M Syed Ali, N Gunasekaran, R Agalya and Y H Joo Int. J. Syst. Sci. 49 3354 (2018)

  21. N Gunasekaran, N M Thoiyab, P Muruganantham, G Rajchakit and B Unyong IEEE Access 8 178108 (2020)

    Article  Google Scholar 

  22. J H Park, T H Lee, Y Liu and J Chen Dynamic Systems with Time Delays: Stability and Control (New York: Springer) (2019)

    Book  MATH  Google Scholar 

  23. R Vadivel, M S Ali and Y H Joo J. Franklin Inst. 357 4079 (2020)

    Article  MathSciNet  Google Scholar 

  24. K Mathiyalagan, R Sakthivel and S M Anthoni Int. J. Adapt. Control Signal Process. 28 429 (2014)

    Article  Google Scholar 

  25. C K Ahn Modern Physics Letters B 24 1217 (2010)

  26. Z Zhang, X Huang, Y Chen and J Zhou Int. J. Adapt. Control Signal Process. 35 1438 (2021)

    Article  Google Scholar 

  27. X Liao, S Yang, S Cheng and Y Fu Sci. China Ser. F Inf. Sci. 44 389 (2001)

    Article  Google Scholar 

  28. L Wang and D Xu Sci. China Ser. F Inf. Sci. 46 466 (2003)

    Article  Google Scholar 

  29. J Lu IEEE Trans. Circuits Syst. II Express Briefs 54 1115 (2007)

  30. T Wei, P Lin, Q Zhu and Y Wang IEEE Trans. Neural Netw. Learn. Syst. 30 1575 (2018)

    Article  Google Scholar 

  31. J Zhou, Y Liu, J Xia, Z Wang and S Arik Neural Netw. 125 194 (2020)

    Article  Google Scholar 

  32. J Lin, R Xu and X Tian Int. J. Bifurcat Chaos 29 1950154 (2019)

    Article  Google Scholar 

  33. L Duan, L Huang, Z Guo and X Fang Comput. Math. Appl. 73 233 (2017)

    Article  MathSciNet  Google Scholar 

  34. Q Yao, L Wang and Y Wang Commun. Nonlinear Sci. Numer. Simul. 78 104865 (2019)

    Article  MathSciNet  Google Scholar 

  35. W Tai, D Xu, T Guo and J Zhou Mod. Phys. Lett. B 35 2150434 (2021)

    Article  ADS  Google Scholar 

  36. T Li and W Zheng Int. J. Syst. Sci. 46 831 (2015)

    Article  Google Scholar 

  37. J Zhou, S Xu, B Zhang, Y Zou and H Shen IEEE Trans. Neural Netw. Learn. Syst. 23 1407 (2012)

    Article  Google Scholar 

  38. K Gu, J Chen and V L Kharitonov Stability of Time-Delay Systems (Berlin: Springer)) (2003)

    Book  MATH  Google Scholar 

  39. M L Boas Mathematical Methods in the Physical Sciences. (New York: Wiley) (2006).

  40. N Gunasekaran, N M Thoiyab, Q Zhu, J Cao and P Muruganantham IEEE Trans. Cybern. 1-11 (2021)

  41. Z Yan, X Huang, Y Fan, J Xia and H Shen IEEE Trans. Syst. Man Cybern. Syst. 51 6712 (2021)

    Article  Google Scholar 

  42. S Santra, H R Karimi, R Sakthivel and S M Anthoni Int. J. Control Autom. Syst. 14 39 (2016)

    Article  Google Scholar 

  43. M Syed Ali, N Gunasekaran and Y H Joo Neural Process. Lett. 50 357 (2019)

  44. Y Cao, W Jiang and J Wang Knowl.-Based Syst. 233 107539 (2021)

  45. M Wu, Y He and J H She Stability Analysis and Robust Control of Time-Delay Systems (Berlin: Springer) 22 (2010)

Download references

Author information

Authors and Affiliations

  1. Research Institute of Information Technology, Anhui University of Technology, Ma’anshan, 243000, China

    Weipeng Tai, Dandan Gao, Jianping Zhou & Xiaolin Wang

  2. School of Computer Science and Technology, Anhui University of Technology, Ma’anshan, 243032, China

    Weipeng Tai & Jianping Zhou

Authors
  1. Weipeng Tai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dandan Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jianping Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xiaolin Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jianping Zhou.

Ethics declarations

Conflict of interest

The authors declare no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tai, W., Gao, D., Zhou, J. et al. \(\mathcal{H}_{\infty }\) weight learning of dynamic neural networks with delay and reaction–diffusion. Indian J Phys 97, 819–828 (2023). https://doi.org/10.1007/s12648-022-02464-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12648-022-02464-3

Keywords

Search

Navigation