Exponential stability analysis of time-varying delay neural networks by the creation of experimental Lyapunov functionals
Abstract
This study examines neural network systems exponential stability, a critical characteristic that guarantees the bounded ness and long-term convergence of network states. Using Linear matrix inequality and Lyapunov functional methods, we prove sufficient conditions for exponential stability. The system's state trajectory converges exponentially to an equilibrium point under suitable conditions, as demonstrated by the stability criteria derived from the network's weight matrices, activation functions, and time delays. Our results are validated by theoretical proofs and numerical simulations, showing the usefulness of the findings for control systems, computational neuroscience, and deep learning architectures.
Downloads
References
Thuan, M. V., Trinh, H., and Hien, L. V., New inequality-based approach to passivity analysis of neural networks with interval time-varying delay, Neurocomputing, 194, 301–307 (2016). DOI: 10.1016/j.neucom.2016.02.051
He, Y., Ji, M.-D., Zhang, C.-K., and Wu, M., Global exponential stability of neural networks with time-varying delay based on free-matrix-based integral inequality, Neural Networks, 77, 80–86 (2016). DOI: 10.1016/j.neunet.2016.02.002
Ding, S., Wang, Z., Wu, Y., and Zhang, H., Stability criterion for delayed neural networks via Wirtinger-based multiple integral inequality, Neurocomputing, 214, 53–60 (2016). DOI: 10.1016/j.neucom.2016.04.058
Zeng, H.-B., Park, J. H., Zhang, C.-F., and Wang, W., Stability and dissipativity analysis of static neural networks with interval time-varying delay, J. Franklin Inst., 352(3), 1284–1295 (2015). DOI: 10.1016/j.jfranklin.2014.12.023
Wang, Z., Ding, S., Shan, Q., and Zhang, H., Stability of recurrent neural networks with time-varying delay via flexible terminal method, IEEE Trans. Neural Netw. Learn. Syst., 28(10), 2456–2463 (2017). DOI: 10.1109/TNNLS.2016.2578309
Sheng, Y., Shen, Y., and Zhu, M., Delay-dependent global exponential stability for delayed recurrent neural networks, IEEE Trans. Neural Netw. Learn. Syst., (to appear, 2023).
Zhang, C.-K., He, Y., Jiang, L., and Wu, M., Notes on stability of time-delay systems: Bounding inequalities and augmented Lyapunov–Krasovskii functionals, IEEE Trans. Autom. Control, 62(10), 5331–5336 (2017). DOI: 10.1109/TAC.2016.2635381
Zhang, C.-K., He, Y., Jiang, L., Wu, M., and Zeng, H.-B., Delay-variation-dependent stability of delayed discrete-time systems, IEEE Trans. Autom. Control, 61(9), 2663–2669 (2016). DOI: 10.1109/TAC.2015.2503047
Zhang, C.-K., He, Y., Jiang, L., Wu, Q. H., and Wu, M., Delay-dependent stability criteria for generalized neural networks with two delay components, IEEE Trans. Neural Netw. Learn. Syst., 25(7), 1263–1276 (2014). DOI: 10.1109/TNNLS.2013.2284968
Zhang, X.-M., and Han, Q.-L., Global asymptotic stability analysis for delayed neural networks using a matrix-based quadratic convex approach, Neural Networks, 54, 57–69 (2014). DOI: 10.1016/j.neunet.2014.02.012
Kwon, O.-M., Park, M.-J., Lee, S.-M., Park, J. H., and Cha, E.-J., Stability for neural networks with time-varying delays via some new approaches, IEEE Trans. Neural Netw. Learn. Syst., 24(2), 181–193 (2013). DOI: 10.1109/TNNLS.2012.2224883
Kwon, O.-M., Park, J. H., Lee, S.-M., and Cha, E.-J., Analysis on delay-dependent stability for neural networks with time-varying delays, Neurocomputing, 103, 114–120 (2013). DOI: 10.1016/j.neucom.2012.09.012
Kwon, O.-M., Park, J. H., Lee, S.-M., and Cha, E.-J., New augmented Lyapunov–Krasovskii functional approach to stability analysis of neural networks with time-varying delays, Nonlinear Dyn., 76(1), 221–236 (2014). DOI: 10.1007/s11071-013-1122-2
Ji, M.-D., He, Y., Zhang, C.-K., and Wu, M., Novel stability criteria for recurrent neural networks with time-varying delay, Neurocomputing, 138, 383–391 (2014). DOI: 10.1016/j.neucom.2014.01.024
Zhang, C.-K., Jiang, L., He, Y., Wu, H., and Wu, M., Stability analysis for control systems with aperiodically sampled data using an augmented Lyapunov functional method, IET Control Theory Appl., 7(9), 1219–1226 (2013). DOI: 10.1049/iet-cta.2012.0814
Zhang, C.-K., He, Y., Jiang, L., Wu, M., and Wu, Q. H., Stability analysis of sampled-data systems considering time delays and its application to electric power markets, J. Franklin Inst., 351(9), 4457–4478 (2014). DOI: 10.1016/j.jfranklin.2014.05.014
Lee, T. H., and Park, J. H., Improved criteria for sampled-data synchronization of chaotic Lur’e systems using two new approaches, Nonlinear Anal., Hybrid Syst., 24, 132–145 (2017). DOI: 10.1016/j.nahs.2016.11.006
Lee, T. H., and Park, J. H., Stability analysis of sampled-data systems via free-matrix-based time-dependent discontinuous Lyapunov approach, IEEE Trans. Autom. Control, 62(7), 3653–3657 (2017). DOI: 10.1109/TAC.2017.2670786
Lee, T. H., Trinh, H. M., and Park, J. H., Stability analysis of neural networks with time-varying delay by constructing novel Lyapunov functionals, IEEE Trans. Neural Netw. Learn. Syst., 29(9), 4238–4247 (2018). DOI: 10.1109/TNNLS.2017.2760979
Baskar, P., Anand, K. S., and Umesha, V., Asymptotic stability analysis of neutral time-delay systems with nonlinear uncertainty, Southeast Asian J. Math. Math. Sci., 15(2), 43–56 (2019).
Umesha, V., Padmanabhan, S., Baskar, P., and Ali, M. S., Exponential stability analysis for delay-differential systems of neutral type with an LMI approach, Khayyam J. Math., 5(1), 11–20 (2019).
Saravanan, S., Umesha, V., Ali, M. S., and Padmanabhan, S., Exponential passivity for uncertain neural networks with time-varying delays based on weighted integral inequalities, Neurocomputing, 314, 429–436 (2018). DOI: 10.1016/j.neucom.2018.07.009
Ravi Chandra, S., Padmanabhan, S., Umesha, V., Ali, M. S., Rajchakit, G., and Jirawattanapanit, A., New insights on bidirectional associative memory neural networks with leakage delay components and time-varying delays using sampled-data control, Neural Process. Lett., 56(2), 94–108 (2024). DOI: 10.1007/s11063-024-11499-y
Ravi Chandra, S., Rajakumari, P., Shanthi, G., Baskar, P., Umesha, V., and Padmanabhan, S., Control of sampled data for neural networks with time-varying and leakage delays, Int. J. Inf. Technol., 31, 1–6 (2025). DOI: 10.1007/s41870-025-02518-9
Copyright (c) 2026 Boletim da Sociedade Paranaense de Matemática
This work is licensed under a Creative Commons Attribution 4.0 International License.
When the manuscript is accepted for publication, the authors agree automatically to transfer the copyright to the (SPM).
The journal utilize the Creative Common Attribution (CC-BY 4.0).
