Impulsive Control on the Exponential Stability of Neural Networks Involving Conformable Derivative

Abstract

Exponential stability of an impulsive artificial neural network model is investigated using a Lyapunov function. Impulsive control mechanisms, characterized by discrete and sudden interventions, are analyzed for their profound impact on the dynamical behavior of neural networks. It is shown that the stability of the equilibrium depends on the impulse effect.

Keywords

• Neural networks
• exponential stability
• impulsive control
• conformable derivative
• Lyapunov function

References

1. Abdeljawad, T. (2015). On conformable fractional calculus. J. Comput. Appl. Math., 279:57–66.
2. Agarwal, R., Hristova, S., O’Regan, D., and Terzieva, R. (2019). Stability properties of neural networks with non-instantaneous impulses. Math Biosci Eng., 16(3):1210–1227.
3. Akhmet, M., Arugaslan, D., and Cengiz, N. (2018). Exponential stability of periodic solutions of recurrent neural networks with functional dependence on piecewise constant argument. Turkish Journal of Mathematics, 42(1):272–292.
4. Akhmet, M. and Fen, M. (2016). Replication of Chaos in Neural Networks, Economics and Physics. Springer, Berlin, Heidelberg.
5. Akhmet, M. and Karacaoren, M. (2018). A Hopfield neural network with multi-compartmental activation. Neural Comput. Appl., 29:815–822.
6. Boroomand, A. and Menhaj, M. (2009). Fractional-order Hopfield neural networks. In Köppen, M., Kasabov, N., and Coghill, G., editors, Advances in Neuro-Information Processing. ICONIP 2008, volume 5506 of Lecture Notes in Computer Science. Springer, Berlin, Heidelberg.
7. Cao, J., Chen, A., and Huang, X. (2005). Almost periodic attractor of delayed neural networks with variable coefficients. Physics Letters A, 340:104–120.
8. Cao, Y. and Bai, C. (2014). Finite-time stability of fractional-order BAM neural networks with distributed delay. Abstr. Appl. Anal., pages 1–8.

9. Cao, Y. and Bai, C. (2015). Existence and stability analysis of fractional order BAM neural networks with a time delay. Applied Mathematics, 6:2057–2068.
10. Chen, L., Chai, Y., Wu, R., Ma, T., and Zhai, H. (2013). Dynamic analysis of a class of fractional-order neural networks with delay. Neurocomputing, 111:190–194.
11. Chiu, K. (2017). Exponential stability and periodic solutions of impulsive neural network models with piecewise constant argument. Acta Appl. Math., 151:199–226.
12. Chiu, K. (2022a). Analyzing stability of equilibrium points in impulsive neural network models involving generalized piecewise alternately advanced and retarded argument. Tamkang Journal of Mathematics, 54(4):379–404.
13. Chiu, K. (2022b). Existence and global exponential stability of equilibrium for impulsive neural network models with generalized piecewise constant delay. Asian-European Journal of Mathematics, 15(01):2250001.
14. Chiu, K. (2022c). Periodicity and stability analysis of impulsive neural network models with generalized piecewise constant delays. Discrete and Continuous Dynamical Systems - B, 27(2):659–689.
15. Cui, P. and Li, Z. (2017). Anti-periodic solutions for BAM-type Cohen-Grossberg neural networks with time delays. J. Nonlinear Sci. Appl., 10(4):2171–2180.
16. Demirci, E., Karakoç, F., and Kütahyalıoğlu, A. (2024). Mittag-Leffler stability of neural networks with Caputo–Hadamard fractional derivative. Math. Meth. Appl. Sci., 47:10091–10100.
17. Ding, K. and Zhu, Q. (2020). Impulsive method to reliable sampled-data control for uncertain fractional-order memristive neural networks with stochastic sensor faults and its applications. Nonlinear Dyn, 100:2595–2608.
18. Fausett, L. and Fausett, L. (1994). Fundamentals of Neural Networks: Architectures, Algorithms, and Applications. Prentice-Hall.
19. Fu, Q., Cai, J., and Zhong, S. (2019). Pinning impulsive synchronization of stochastic memristor-based neural networks with time-varying delays. Int. J. Control Autom. Syst., 17:243–252.
20. Gopalsamy, K. (2004). Stability of artificial neural networks with impulses. Appl. Math. Comput., 154:783–813.
21. Guan, Z. and Chen, G. (1999). On delayed impulsive Hopfield neural networks. Neural Networks, 12(2):273–280.
22. Hopfield, J. (1982). Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. U.S.A., 79(8):2554–2558.
23. Hopfield, J. (1984). Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Natl. Acad. Sci. U.S.A., 81:3088–3092.
24. Huyen, N., Sau, N., and Thuan, M. (2022). LMI conditions for fractional exponential stability and passivity analysis of uncertain Hopfield conformable fractional-order neural networks. Neural Process Lett., 54:1333–1350.
25. Jiang, H. and Cao, J. (2008). BAM-type Cohen–Grossberg neural networks with time delays. Mathematical and Computer Modelling, 47:92–103.
26. Ke, Y. and Miao, C. (2015). Stability analysis of fractional-order Cohen–Grossberg neural networks with time delay. Int. J. Comput. Math., 92(6):1102–1113.
27. Khalil, R., Al Horani, M., Yousef, A., and Sababheh, M. (2014). A new definition of fractional derivative. J. Comput. Appl. Math., 264:65–70.
28. Kütahyalıoğlu, A. and Karakoç, F. (2021). Exponential stability of Hopfield neural networks with conformable fractional derivative. Neurocomputing, 456:263–267.
29. Kutahyalioglu, A. and Karakoç, F. (2023). Exponential stability of BAM-type neural networks with conformable derivative. Proceedings of the Institute of Mathematics and Mechanics, 49(1):78–94.
30. Lakshmikantham, V., Bainov, D., and Simeonov, P. (1989). Theory of Impulsive Differential Equations. Series in Modern Applied Mathematics. World Scientific.
31. Li, R., Wu, H., and Cao, J. (2022). Impulsive exponential synchronization of fractional-order complex dynamical networks with derivative couplings via feedback control based on discrete time state observations. Acta Math Sci, 42:737–754.
32. Li, Y. and Lu, L. (2004). Global exponential stability and existence of periodic solution of Hopfield-type neural networks with impulses. Physics Letters A, 333(1–2):62–71.
33. Liu, D. and Ye, D. (2020). Exponential synchronization of memristive delayed neural networks via event-based impulsive control method. Journal of the Franklin Institute, 357(7):4437–4457.
34. Lundstrom, B., Higgs, M., Spain, W., and Fairhall, A. (2008). Fractional differentiation by neocortical pyramidal neurons. Nature Neuroscience, 11(11):1335–1342.
35. McCulloch, W. and Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophysics, 5:115–133.
36. Mohamad, S. (2001). Global exponential stability in continuous-time and discrete time delayed bidirectional neural networks. Physica D: Nonlinear Phenomena, 159:233–251.
37. Mohamad, S. and Gopalsamy, K. (2003). Exponential stability of continuous-time and discrete-time cellular neural networks with delays. Applied Mathematics and Computation, 135(1):17–38.
38. Pinto, M., Torres, R., and Sepulveda, D. (2018). Exponential periodic attractor of impulsive Hopfield- type neural network system with piecewise constant argument. Electronic Journal of Qualitative Theory of Differential Equations, 34:1–28.
39. Samoilenko, A. and Perestyuk, N. (1995). Impulsive Differential Equations. World Scientific, Singapore.
40. Solís-Pérez, J., Hernández, J., Parrales, A., Gómez-Aguilar, J., and Huicochea, A. (2022). Artificial neural networks with conformable transfer function for improving the performance in thermal and environmental processes. Neural Networks, 152:44–56.
41. Song, Q. and Cao, J. (2014). Dynamics in fractional-order neural networks. Neurocomputing, 142:494– 498.
42. Srivastava, H., Abbas, S., Tyagi, S., and Lassoued, D. (2018). Global exponential stability of fractional- order impulsive neural network with time-varying and distributed delay. Math Meth Appl Sci., 41:2095– 2104.
43. Stamova, I. (2014). Global Mittag-Leffler stability and synchronization of impulsive fractional-order neural networks with time-varying delays. Nonlinear Dyn., 77:1251–1260.
44. Stamova, I., Stamov, T., and Simeonova, N. (2013). Impulsive control on global exponential stability for cellular neural networks with supremums. Journal of Vibration and Control, 19(4):483–490.
45. Stamova, I., Stamov, T., and Simeonova, N. (2014). Impulsive effects on the global exponential stability of neural network models with supremums. European Journal of Control, 20:199–206.
46. Tang, Z., Luo, Y., and Deng, F. (2005). Global exponential stability of reaction-diffusion Hopfield neural networks with distributed delays. In Advances in Neural Networks, volume 3496 of Lecture Notes in Computer Science, pages 174–180. Springer, Berlin, Heidelberg.
47. Wang, L. and Zou, X. (2002). Exponential stability of Cohen-Grossberg neural networks. Neural Networks, 15:415–422.
48. Xiao, S. and Li, J. (2023). Exponential stability of impulsive conformable fractional-order nonlinear differential system with time-varying delay and its applications. Neurocomputing, 560:126845.
49. Yadav, N., Yadav, A., and Kumar, M. (2015). An Introduction to Neural Network Methods for Differential Equations. Springer, Dordrecht.
50. Yang, X., Song, Q., Liu, Y., and Zhao, Z. (2014). Uniform stability analysis of fractional-order BAM neural networks with delays in the leakage terms. Abstr. Appl. Anal., pages 1–16.
51. Zhang, S., Yu, Y., and Wang, H. (2015). Mittag-Leffler stability of fractional-order Hopfield neural networks. Nonlinear Analysis: Hybrid Systems, 16:104–121.
52. Zhao, D. and Luo, M. (2017). General conformable fractional derivative and its physical interpretation. Calcolo, 54:903–917.