Stability analysis for bidirectional associative memory neural networks: A new global asymptotic approach

N. Mohamed Thoiyab; Mostafa Fazly; R. Vadivel; Nallappan Gunasekaran; N. Mohamed Thoiyab; Mostafa Fazly; R. Vadivel; Nallappan Gunasekaran

doi:10.3934/math.2025182

AIMS Mathematics

2025, Volume 10, Issue 2: 3910-3929. doi: 10.3934/math.2025182

Previous Article Next Article

Research article Special Issues

Stability analysis for bidirectional associative memory neural networks: A new global asymptotic approach

1.
Department of Mathematics, Jamal Mohamed College, Affiliated to Bharathidasan University, Tiruchirappalli 620020, Tamilnadu, India
2.
Department of Mathematics, University of Texas at San Antonio, San Antonio, TX 78249, United States of America
3.
Department of Mathematics, Faculty of Science and Technology, Phuket Rajabhat University, Phuket-83000, Thailand
4.
Department of Natural Sciences, Eastern Michigan Joint College of Engineering, Beibu Gulf University, Qinzhou 535011, China

Received: 05 December 2024 Revised: 02 February 2025 Accepted: 18 February 2025 Published: 26 February 2025
MSC : 93D05, 34D23, 34D08, 68T07, 68T07

This study employs specific and appropriate criteria to investigate the global stability of hybrid bidirectional associative memory (BAM) neural networks with time delays. We establish new and more general conditions for global asymptotic robust stability (GARS) in time-delayed BAM neural networks at the equilibrium point. This represents the primary objective and novelty of this paper. The derived conditions are independent of the system parameter delay in BAM neural networks. Finally, we provide numerical examples to illustrate the applicability and effectiveness of our conclusions with respect to network parameters.
- asymptotic stability,
- BAM,
- interval matrices,
- LKF,
- time-delay
Citation: N. Mohamed Thoiyab, Mostafa Fazly, R. Vadivel, Nallappan Gunasekaran. Stability analysis for bidirectional associative memory neural networks: A new global asymptotic approach[J]. AIMS Mathematics, 2025, 10(2): 3910-3929. doi: 10.3934/math.2025182

Related Papers:

Abstract

This study employs specific and appropriate criteria to investigate the global stability of hybrid bidirectional associative memory (BAM) neural networks with time delays. We establish new and more general conditions for global asymptotic robust stability (GARS) in time-delayed BAM neural networks at the equilibrium point. This represents the primary objective and novelty of this paper. The derived conditions are independent of the system parameter delay in BAM neural networks. Finally, we provide numerical examples to illustrate the applicability and effectiveness of our conclusions with respect to network parameters.

References

[1]	J. X. Peng, K. Li, G. W. Irwin, A new Jacobian matrix for optimal learning of single-layer neural networks, IEEE T. Neural Networ., 19 (2008), 119–129. https://doi.org/10.1109/TNN.2007.903150 doi: 10.1109/TNN.2007.903150
[2]	Z. Zhai, H. Yan, S. Chen, Y. Chang, C. Chen, Hierarchical stability conditions for generalized neural networks with interval time-varying delay, IEEE T. Syst. Man Cyb. Sys., 55 (2025), 418–429. https://doi.org/10.1109/TSMC.2024.3475483 doi: 10.1109/TSMC.2024.3475483
[3]	P. Kowsalya, S. Kathiresan, A. Kashkynbayev, R. Rakkiyappan, Fixed-time synchronization of delayed multiple inertial neural network with reaction-diffusion terms under cyber-physical attacks using distributed control and its application to multi-image encryption, Neural Networks, 180 (2024), 106743. https://doi.org/10.1016/j.neunet.2024.106743 doi: 10.1016/j.neunet.2024.106743
[4]	P. Gokul, G. Soundararajan, A. Kashkynbayev, R. Rakkiyappan, Finite-time contractive stability for fractional-order nonlinear systems with delayed impulses: Applications to neural networks, Neurocomputing, 610 (2024), 128599. https://doi.org/10.1016/j.neucom.2024.128599 doi: 10.1016/j.neucom.2024.128599
[5]	L. Wan, Q. Zhou, H. Fu, Q. Zhang, Exponential stability of hopfield neural networks of neutral type with multiple time-varying delays, AIMS Math., 6 (2021), 8030–8043. http://dx.doi.org/10.3934/math.2021466 doi: 10.3934/math.2021466
[6]	J. Lan, X. Zhang, X. Wang, Global robust exponential stability of interval BAM neural networks with multiple time-varying delays: A direct method based on system solutions, ISA T., 144 (2024), 145–152. https://doi.org/10.1016/j.isatra.2023.11.001 doi: 10.1016/j.isatra.2023.11.001
[7]	N. Gunasekaran, N. M. Thoiyab, P. Muruganantham, G. Rajchakit, B. Unyong, Novel results on global robust stability analysis for dynamical delayed neural networks under parameter uncertainties, IEEE Access, 8 (2020), 178108–178116. https://doi.org/10.1109/ACCESS.2020.3016743 doi: 10.1109/ACCESS.2020.3016743
[8]	N. M. Thoiyab, P. Muruganantham, G. Rajchakit, N. Gunasekaran, B. Unyong, U. Humphries, et al., Global stability analysis of neural networks with constant time delay via frobenius norm, Math. Probl. Eng., 2020 (2020), 4321312. https://doi.org/10.1155/2020/4321312 doi: 10.1155/2020/4321312
[9]	S. Arik, New criteria for stability of neutral-type neural networks with multiple time delays, IEEE T. Neur. Net. Lear., 31 (2020), 1504–1513. https://doi.org/10.1109/TNNLS.2019.2920672 doi: 10.1109/TNNLS.2019.2920672
[10]	H. B. Zeng, Z. J. Zhu, W. Wang, X. M. Zhang, Relaxed stability criteria of delayed neural networks using delay-parameters-dependent slack matrices, Neural Networks, 180 (2024), 106676. https://doi.org/10.1016/j.neunet.2024.106676 doi: 10.1016/j.neunet.2024.106676
[11]	H. C. Lin, H. B. Zeng, X. M. Zhang, W. Wang, Stability analysis for delayed neural networks via a generalized reciprocally convex inequality, IEEE T. Neur. Net. Lear., 34 (2022), 7491–7499. https://doi.org/10.1109/TNNLS.2022.3144032 doi: 10.1109/TNNLS.2022.3144032
[12]	X. M. Sun, W. Wang, G. P. Liu, J. Zhao, Stability analysis for linear switched systems with time-varying delay, IEEE T. Syst. Man Cyb., 38 (2008), 528–533. https://doi.org/10.1109/TSMCB.2007.912078 doi: 10.1109/TSMCB.2007.912078
[13]	N. Gunasekaran, G. Zhai, Q. Yu, Sampled-data synchronization of delayed multi-agent networks and its application to coupled circuit, Neurocomputing, 413 (2020), 499–511. https://doi.org/10.1016/j.neucom.2020.05.060 doi: 10.1016/j.neucom.2020.05.060
[14]	J. L. Shao, T. Z. Huang, S. Zhou, Some improved criteria for global robust exponential stability of neural networks with time-varying delays, Commun. Nonlinear Sci., 15 (2010), 3782–3794. https://doi.org/10.1016/j.cnsns.2010.02.002 doi: 10.1016/j.cnsns.2010.02.002
[15]	B. Kosko, Adaptive bidirectional associative memories, Appl. Opt., 26 (1987), 4947–4960. https://doi.org/10.1364/AO.26.004947 doi: 10.1364/AO.26.004947
[16]	B. Kosko, Bidirectional associative memories, IEEE T. Syst. Man Cyb., 18 (1988), 49–60. https://doi.org/10.1109/21.87054 doi: 10.1109/21.87054
[17]	L. Wang, D. Xu, Global asymptotic stability of bidirectional associative memory neural networks with s-type distributed delays, Int. J. Syst. Sci., 33 (2002), 869–877. https://doi.org/10.1080/00207720210161777 doi: 10.1080/00207720210161777
[18]	U. Humphries, G. Rajchakit, P. Kaewmesri, P. Chanthorn, R. Sriraman, R. Samidurai, et al., Global stability analysis of fractional-order quaternion-valued bidirectional associative memory neural networks, Mathematics, 8 (2020), 801. https://doi.org/10.3390/math8050801 doi: 10.3390/math8050801
[19]	Z. Zhang, F. Lin, Global asymptotic stability of periodic solutions for neutral-type delayed BAM neural networks by combining an abstract theorem of k-set contractive operator with lmi method, Neural Process. Lett., 50 (2019), 1571–1588. https://doi.org/10.1007/s11063-018-9941-2 doi: 10.1007/s11063-018-9941-2
[20]	D. Gao, J. Li, Global asymptotic stability of periodic solutions for neutral-type BAM neural networks with delays, Neural Process. Lett., 51 (2020), 367–382. https://doi.org/10.1007/s11063-019-10092-y doi: 10.1007/s11063-019-10092-y
[21]	L. Duan, J. Li, Finite-time synchronization for a fully complex-valued bam inertial neural network with proportional delays via non-reduced order and non-separation approach, Neurocomputing, 611 (2025), 128648. https://doi.org/10.1016/j.neucom.2024.128648 doi: 10.1016/j.neucom.2024.128648
[22]	N. M. Thoiyab, P. Muruganantham, Q. Zhu, N. Gunasekaran, Novel results on global stability analysis for multiple time-delayed bam neural networks under parameter uncertainties, Chaos Soliton. Fract., 152 (2021), 111441. https://doi.org/10.1016/j.chaos.2021.111441 doi: 10.1016/j.chaos.2021.111441
[23]	X. F. Liao, K. W. Wong, Robust stability of interval bidirectional associative memory neural network with time delays, IEEE T. Syst. Man Cyb., 34 (2004), 1142–1154. https://doi.org/10.1109/TSMCB.2003.821455 doi: 10.1109/TSMCB.2003.821455
[24]	W. Yang, W. Yu, J. Cao, Global exponential stability of impulsive fuzzy high-order BAM neural networks with continuously distributed delays, IEEE T. Neur. Net. Learn. Syst., 29 (2017), 3682–3700. https://doi.org/10.1109/TNNLS.2017.2736581 doi: 10.1109/TNNLS.2017.2736581
[25]	P. Muruganantham, N. M. Thoiyab, N. Gunasekaran, A new upper bound for global asymptotic robust stability of BAM neural networks under multiple time-delays, In: First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT), IEEE, 2022, 1–6. https://doi.org/10.1109/ICEEICT53079.2022.9768421
[26]	D. Wang, L. Huang, L. Tang, Dissipativity and synchronization of generalized BAM neural networks with multivariate discontinuous activations, IEEE T. Neur. Net. Learn. Syst., 29 (2017), 3815–3827. https://doi.org/10.1109/TNNLS.2017.2741349 doi: 10.1109/TNNLS.2017.2741349
[27]	X. Lou, B. Cui, Stochastic exponential stability for Markovian jumping BAM neural networks with time-varying delays, IEEE T. Syst. Man Cyb., 37 (2007), 713–719. https://doi.org/10.1109/TSMCB.2006.887426 doi: 10.1109/TSMCB.2006.887426
[28]	N. M. Thoiyab, P. Muruganantham, N. Gunasekaran, Global robust stability analysis for hybrid BAM neural networks, In: IEEE second international conference on control, measurement and instrumentation, IEEE, 2021, 93–98. https://doi.org/10.1109/CMI50323.2021.9362980
[29]	S. Senan, S. Arik, Global robust stability of bidirectional associative memory neural networks with multiple time delays, IEEE T. Syst. Man Cyb., 37 (2007), 1375–1381. https://doi.org/10.1109/TSMCB.2007.902244 doi: 10.1109/TSMCB.2007.902244
[30]	S. Arik, Global robust stability of delayed neural networks, IEEE T. Circuits-I Fund. Theor. Appl., 50 (2003), 156–160. https://doi.org/10.1109/TCSI.2002.807515 doi: 10.1109/TCSI.2002.807515
[31]	E. Aktas, O. Faydasicok, S. Arik, Robust stability of dynamical neural networks with multiple time delays: A review and new results, Artif. Intell. Rev., 56 (2023), 1647–1684. https://doi.org/10.1007/s10462-023-10552-x doi: 10.1007/s10462-023-10552-x
[32]	N. Gunasekaran, N. M. Thoiyab, Q. Zhu, J. Cao, P. Muruganantham, New global asymptotic robust stability of dynamical delayed neural networks via intervalized interconnection matrices, IEEE T. Cybernetics, 52 (2022), 11794–11804. https://doi.org/10.1109/TCYB.2021.3079423 doi: 10.1109/TCYB.2021.3079423
[33]	J. Cao, D. S. Huang, Y. Qu, Global robust stability of delayed recurrent neural networks, Chaos Soliton. Fract., 23 (2005), 221–229. https://doi.org/10.1016/j.chaos.2004.04.002 doi: 10.1016/j.chaos.2004.04.002
[34]	M. Liu, H. Jiang, C. Hu, B. Lu, Z. Li, Novel global asymptotic stability and dissipativity criteria of BAM neural networks with delays, Front. Phys., 10 (2022), 898589. https://doi.org/10.3389/fphy.2022.898589 doi: 10.3389/fphy.2022.898589
[35]	M. Chinnamuniyandi, S. Chandran, C. Xu, Fractional order uncertain BAM neural networks with mixed time delays: An existence and quasi-uniform stability analysis, J. Intell. Fuzzy Syst., 46 (2024), 4291–4313. https://doi.org/10.3233/JIFS-234744 doi: 10.3233/JIFS-234744
[36]	X. Li, X. Liu, S. Zhang, New criteria on the finite-time stability of fractional-order BAM neural networks with time delay, Neural Comput. Appl., 34 (2022), 4501–4517. https://doi.org/10.1007/s00521-021-06605-3 doi: 10.1007/s00521-021-06605-3
[37]	Z. Zhang, Z. Quan, Global exponential stability via inequality technique for inertial BAM neural networks with time delays, Neurocomputing, 151 (2015), 1316–1326. https://doi.org/10.1016/j.neucom.2014.10.072 doi: 10.1016/j.neucom.2014.10.072

Reader Comments

Your name:*

Email:*
© 2025 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)