Exponential input-to-state stability for delayed inertial BAM neural networks

Wentao Wang; Wei Chen; Wentao Wang; Wei Chen

doi:10.3934/era.2026259

Electronic Research Archive

2026, Volume 34, Issue 9: 5842-5860. doi: 10.3934/era.2026259

Previous Article Next Article

Research article

Exponential input-to-state stability for delayed inertial BAM neural networks

Wentao Wang ¹,
Wei Chen ^{2
,
,}

1.
School of Mathematics, Physics and Statistics, Shanghai University of Engineering Science, Shanghai 201620, China
2.
School of Statistics and Mathematics, Shanghai Lixin University of Accounting and Finance, Shanghai 201209, China

Received: 26 March 2026 Revised: 17 May 2026 Accepted: 01 July 2026 Published: 09 July 2026

Focusing on delayed inertial bidirectional associative memory (BAM) neural networks, this paper addressed their exponential input-to-state stability (EIS). Rather than relying on conventional reduced-order methods and Lyapunov-Krasovskii functionals (LKFs), we established EIS via the characteristics method by introducing three sufficient conditions cast as linear scalar inequalities. Three illustrative numerical examples, backed by simulation results, confirmed the theoretical conclusions.
- delayed inertial BAM neural networks,
- exponential input-to-state stability,
- global exponential stability,
- characteristics method,
- reduced-order method
Citation: Wentao Wang, Wei Chen. Exponential input-to-state stability for delayed inertial BAM neural networks[J]. Electronic Research Archive, 2026, 34(9): 5842-5860. doi: 10.3934/era.2026259

Related Papers:

Abstract

Focusing on delayed inertial bidirectional associative memory (BAM) neural networks, this paper addressed their exponential input-to-state stability (EIS). Rather than relying on conventional reduced-order methods and Lyapunov-Krasovskii functionals (LKFs), we established EIS via the characteristics method by introducing three sufficient conditions cast as linear scalar inequalities. Three illustrative numerical examples, backed by simulation results, confirmed the theoretical conclusions.

References

[1]	B. Kosko, Adaptive bi-directional associative memories, Appl. Opt., 26 (1987), 4947–4960. https://doi.org/10.1364/AO.26.004947 doi: 10.1364/AO.26.004947
[2]	B. Kosko, Bi-directional associative memories, IEEE Trans. Syst. Man Cybern., 18 (1988), 49–60. https://doi.org/10.1109/21.87054 doi: 10.1109/21.87054
[3]	B. Kosko, Neural Networks and Fuzzy Systems-A Dynamical System Approach Machine Intelligence, Englewood Cliffs, Prentice-Hall, 1992.
[4]	K. Babcock, R. Westervelt, Stability and dynamics of simple electronic neural networks with added inertia, Phys. D Nonlinear Phenom., 23 (1986), 464–469. https://doi.org/10.1016/0167-2789(86)90152-1 doi: 10.1016/0167-2789(86)90152-1
[5]	K. Babcock, R. Westervelt, Dynamics of simple electronic neural networks, Phys. D Nonlinear Phenom., 28 (1987), 305–316. https://doi.org/10.1016/0167-2789(87)90021-2 doi: 10.1016/0167-2789(87)90021-2
[6]	Y. Ke, C. Miao, Stability analysis of BAM neural networks with inertial term and time delay, Wseas. Trans. Syst., 10 (2011), 425–438. https://dl.acm.org/doi/10.5555/2190008.2190011 doi: 10.5555/2190008.2190011
[7]	Y. Ke, C. Miao, Stability and existence of periodic solutions in inertial BAM neural networks with time delay, Neural Comput. Appl., 23 (2013), 1089–1099. https://doi.org/10.1007/s00521-012-1037-8 doi: 10.1007/s00521-012-1037-8
[8]	W. Wang, Mean-square exponential input-to-state stability of stochastic fuzzy delayed Cohen-Grossberg neural networks, J. Exp. Theor. Artif. Intell., 36 (2024), 1823–1836. https://doi.org/10.1080/0952813X.2023.2165725 doi: 10.1080/0952813X.2023.2165725
[9]	J. Liu, J. Jian, B. Wang, Stability analysis for BAM quaternion-valued inertial neural networks with time delay via nonlinear measure approach, Math. Comput. Simulation, 174 (2020), 134–152. https://dx.doi.org/10.1016/j.matcom.2020.03.002 doi: 10.1016/j.matcom.2020.03.002
[10]	Y. Zhang, Z. Li, W. Jiang, W. Liu, The stability of anti-periodic solutions for fractional-order inertial BAM neural networks with time-delays, AIMS Math., 8 (2023), 6176–6190. https://doi.org/10.3934/math.2023312 doi: 10.3934/math.2023312
[11]	H. Liao, Z. Zhang, L. Ren, W. Peng, Global asymptotic stability of periodic solutions for inertial delayed BAM neural networks via novel computing method of degree and inequality techniques, Chaos Solitons Fractals, 104 (2017), 785–787. https://doi.org/10.1016/j.chaos.2017.09.035 doi: 10.1016/j.chaos.2017.09.035
[12]	H. Lin, H. Zeng, X. Zhang, Stability analysis for delayed neural networks via a generalized reciprocally convex inequality, IEEE Trans. Neural Networks Learn. Syst., 34 (2023), 7491–7499. https://doi.org/10.1109/TNNLS.2022.3144032 doi: 10.1109/TNNLS.2022.3144032
[13]	H. Zeng, Z. Zhu, W. Wang, X. 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
[14]	Y. Chen, C. Lu, X. Zhang, Allowable delay set flexible fragmentation approach to passivity analysis of delayed neural networks, Neurocomputing, 629 (2025), 129730. https://doi.org/10.1016/j.neucom.2025.129730 doi: 10.1016/j.neucom.2025.129730
[15]	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
[16]	H. Zeng, Z. Zhu, S. Xiao, X. Zhang, A switched system model for exponential stability and dissipativity of delayed neural networks, IEEE Trans. Neural Networks Learn. Syst., 36 (2025), 19708–19717. https://doi.org/10.1109/TNNLS.2025.3590251 doi: 10.1109/TNNLS.2025.3590251
[17]	N. Cheng, W. Wang, H. Zeng, X. Liu, X. Zhang, Novel exponential-weighted integral inequality for exponential stability analysis of time-varying delay systems, Appl. Math. Lett., 172 (2026), 109730. https://doi.org/10.1016/j.aml.2025.109730 doi: 10.1016/j.aml.2025.109730
[18]	H. Zeng, Y. Chen, Y. He, X. Zhang, A delay-derivative-dependent switched system model method for stability analysis of linear systems with time-varying delay, Automatica, 175 (2025), 112183. https://doi.org/10.1016/j.automatica.2025.112183 doi: 10.1016/j.automatica.2025.112183
[19]	R. Zhao, B. Wang, J. Jian, Lagrange Stability of BAM quaternion-valued inertial neural networks via auxiliary function-based integral inequalities, Neural Process. Lett., 54 (2022), 1351–1369. https://doi.org/10.1007/s11063-021-10685-6 doi: 10.1007/s11063-021-10685-6
[20]	R. Zhao, B. Wang, J. Jian, Global $\mu$-stabilization of quaternion-valued inertial BAM neural networks with time-varying delays via time-delayed impulsive control, Math. Comput. Simul., 202 (2022), 223–245. https://doi.org/10.1016/j.matcom.2022.05.036 doi: 10.1016/j.matcom.2022.05.036
[21]	C. Aouiti, Q. Hui, H. Jallouli, Fixed-time stabilization of fuzzy neutral-type inertial neural networks with time-varying delay, Fuzzy Sets Syst., 411 (2021), 48–67. https://doi.org/10.1016/j.fss.2020.10.018 doi: 10.1016/j.fss.2020.10.018
[22]	L. Duan, J. Li, Fixed-time synchronization of fuzzy neutral-type BAM memristive inertial neural networks with proportional delays, Inf. Sci., 576 (2021), 522–541. https://doi.org/10.1016/j.ins.2021.06.093 doi: 10.1016/j.ins.2021.06.093
[23]	H. Wu, X. Zhao, L. Wang, J. Cao, Observer-based fixed-time topology identification and synchronization for complex networks via quantized pinning control strategy, Appl. Math. Comput., 507 (2025), 129568. https://doi.org/10.1016/j.amc.2025.129568 doi: 10.1016/j.amc.2025.129568
[24]	D. Chen, Z. Zhang, Finite-time synchronization for delayed BAM neural networks by the approach of the same structural functions, Chaos Solitons Fractals, 164 (2022), 112655. https://doi.org/10.1016/j.chaos.2022.112655 doi: 10.1016/j.chaos.2022.112655
[25]	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
[26]	X. Hou, H. Wu, J. Cao, Practical finite-time synchronization for Lur'e systems with performance constraint and actuator faults: A memory-based quantized dynamic event-triggered control strategy, Appl. Math. Comput., 487 (2025), 129108. https://doi.org/10.1016/j.amc.2024.129108 doi: 10.1016/j.amc.2024.129108
[27]	Q. Peng, J. Jian, Synchronization analysis of fractional-order inertial type neural networks with time delays, Math. Comput. Simul., 205 (2023), 62–77. https://doi.org/10.1016/j.matcom.2022.09.023 doi: 10.1016/j.matcom.2022.09.023
[28]	J. Cao, Y. Wan, Matrix measure strategies for stability and synchronization of inertial BAM neural network with time delays, Neural Networks, 53 (2014), 165–172. https://doi.org/10.1016/j.neunet.2014.02.003 doi: 10.1016/j.neunet.2014.02.003
[29]	X. Ma, B. Liu, X. Jia, X. Zhang, Synchronization control of chaotic neural networks subject to actuator saturation under event-triggered sampling scheme, Neurocomputing, 677 (2026), 133038. https://doi.org/10.1016/j.neucom.2026.133038 doi: 10.1016/j.neucom.2026.133038
[30]	X. Zhao, H. Wu, J. Cao, L. Wang, Prescribed-time synchronization for complex dynamic networks of piecewise smooth systems: A hybrid event-triggering control approach, Qual. Theory Dyn. Syst., 24 (2025), 11. https://doi.org/10.1007/s12346-024-01166-x doi: 10.1007/s12346-024-01166-x
[31]	E. D. Sontag, Smooth stabilization implies coprime factorization, IEEE Trans. Automat. Control, 34 (1989), 435–443. https://doi.org/10.1109/9.28018 doi: 10.1109/9.28018
[32]	Y. Jiang, S. Zhu, X. Liu, S. Wen, C. Mu, Input-to-state stability of delayed memristor-based inertial neural networks via non-reduced order method, Neural Networks, 178 (2024), 106545. https://doi.org/10.1016/j.neunet.2024.106545 doi: 10.1016/j.neunet.2024.106545
[33]	W. Zhang, J. Qi, X. He, Input-to-state stability of impulsive inertial memristive neural networks with time-varying delayed, J. Franklin Inst., 355 (2018), 8971–8988. https://doi.org/10.1016/j.jfranklin.2018.10.008 doi: 10.1016/j.jfranklin.2018.10.008
[34]	M. Iswarya, R. Raja, J. Cao, M. Niezabitowski, J. Alzabut, C. Maharajan, New results on exponential input-to-state stability analysis of memristor based complex-valued inertial neural networks with proportional and distributed delays, Math. Comput. Simul., 201 (2022), 440–461. https://doi.org/10.1016/j.matcom.2021.01.020 doi: 10.1016/j.matcom.2021.01.020
[35]	S. Chang, Y. Wang, X. Zhang, X. Wang, A new method to study global exponential stability of inertial neural networks with multiple time-varying transmission delays, Math. Comput. Simul., 211 (2023), 329–340. https://doi.org/10.1016/j.matcom.2023.04.008 doi: 10.1016/j.matcom.2023.04.008
[36]	W. Wang, J. Wu, W. Chen, The characteristics method to study global exponential stability of delayed inertial neural networks, Math. Comput. Simul., 232 (2025), 91–101. https://doi.org/10.1016/j.matcom.2024.12.021 doi: 10.1016/j.matcom.2024.12.021
[37]	W. Wang, W. Zeng, W. Chen, Global exponential stability of periodic solutions for inertial delayed BAM neural networks, Commun. Nonlinear Sci. Numer. Simul., 145 (2025), 108728. https://doi.org/10.1016/j.cnsns.2025.108728 doi: 10.1016/j.cnsns.2025.108728
[38]	W. Wang, W. Zeng, W. Chen, New sufficient conditions on the global exponential stability of delayed inertial neural networks, Neurocomputing, 622 (2025), 129301. https://doi.org/10.1016/j.neucom.2024.129301 doi: 10.1016/j.neucom.2024.129301
[39]	Q. Wang, L. Duan, L. Huang, Z. Su, Global exponential stability of a periodic inertial memristive neural networks with time delays: characteristic approach, Neurocomputing, 668 (2026), 132408. https://doi.org/10.1016/j.neucom.2025.132408 doi: 10.1016/j.neucom.2025.132408
[40]	W. Wang, W. Chen, New study on neutral-type inertial BAM neural networks via the characteristic method, J. Math. Anal. Appl., 557 (2026), 130325. https://doi.org/10.1016/j.jmaa.2025.130325 doi: 10.1016/j.jmaa.2025.130325
[41]	W. Wang, Further results on mean-square exponential input-to-state stability of stochastic delayed Cohen-Grossberg neural networks, Neural Process. Lett., 55 (2023), 3953–3965. https://doi.org/10.1007/s11063-022-10974-8 doi: 10.1007/s11063-022-10974-8
[42]	W. Wang, Mean-square exponential input-to-state stability of stochastic delayed recurrent neural networks with local Lipschitz condition, Math. Meth. Appl. Sci., 46 (2023), 17788–17797. https://doi.org/10.1002/mma.9531 doi: 10.1002/mma.9531

Reader Comments

Your name:*

Email:*
© 2026 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)