STABILITY OF NEURAL NETWORKS WITH RANDOM IMPULSES

TitleSTABILITY OF NEURAL NETWORKS WITH RANDOM IMPULSES
Publication TypeJournal Article
Year of Publication2018
AuthorsHRISTOVA SNEZHANA, KOPANOV PETER
JournalDynamic Systems and Applications
Volume27
Issue4
Start Page791
Pagination12
Date Published10/2018
ISSN1056-2176
AMS Subject Classification34A37, 34D20, 34F99, 92B20
Abstract

One of the main properties of solutions of neural networks is stability and often the direct Lyapunov method is used to study stability properties. We consider the Hopfield’s graded response neural network in the case when the neurons are subject to a certain impulsive state displacement at random exponentially distributed moments. It changes significantly the behavior of the solutions because they are not deterministic ones but they are stochastic processes. We examine the stability of the equilibrium of the model. Some sufficient conditions for p-moment stability of equilibrium of neural networks with time varying self-regulating parameters of all units and time varying functions of the connection between two neurons in the network are obtained. These sufficient conditions are explicitly expressed in terms of the parameters of the system and hence they are easily verifiable. We illustrate our theory on a particular nonlinear neural network.
PDFhttps://acadsol.eu/dsa/articles/27/4/7.pdf
DOI10.12732/dsa.v27i4.7
Refereed DesignationRefereed
Full Text

REFERENCES

[1] R. P. Agarwal, S. Hristova, D. O’Regan, P. Kopanov, p-moment exponential stability of differential equations with random impulses and the Erlang distribution, Mem. Diff. Eq,d Math. Phys., 70 (2017),99-106.
[2] R. P. Agarwal, S. Hristova, D. O’Regan, P. Kopanov, Impulsive differential equations with Gamma distributed moments of impulses and p-moment exponential stability, Acta Math. Sci., 37 , No. 4 (2017), 985-997
[3] R. Agarwal, S. Hristova, D. O’Regan, Exponential stability for differential equations with random impulses at random times, Adv. Diff. Eq., 2013 (2013), 372, 12p.
[4] K. Gopalsamy, Stability of artificial neural networks with impulses, Appl. Math. Comput., 154 (2004), 783-813.
[5] J.J. Hopfield, Neural networks and physical systems with emergent collective computational abilities, Proc. Nat. Acad. Sci. USA, 79 (1982), 2554-2558.
[6] R. Rakkiyappan, P. Balasubramaiam, J. Cao, Global exponential stability of neutral-type impulsive neural networks, Nonlinear Anal. Real World Appl., 11 (2010), 122-130.
[7] S. Scardapane, D.Wang, Randomness in neural networks: An overview, WIREs Data Mining Knowl. Discov., 7 (2017), 1-18.
[8] X. Song, P. Zhao, Z. Xing, J. Peng, Global asymptotic stability of CNNs with impulses and multi-proportional delays, Math. Methods Appl. Sci., 39 (2016), 722-733.
[9] A. Vinodkumar, R. Rakkiyappan, Exponential stability results for fixed and random type impulsive Hopfield neural networks, Int. J. Comput. Sci. Math., 7, No. 1 (2016), 1-19.
[10] Z.Wu, Ch. Li, Exponential stability analysis of delayed neural networks with impulsive time window, Advanced Computational Intelligence (ICACI), 2017 Ninth International Conference on, 2017, 37-42.
[11] Z. Yang, D. Xu, Stability analysis of delay neural networks with impulsive effects, IEEE Transactions on Circuits and Systems II: Express Briefs , 52, No. 8, (2015), 517-521.
[12] Q. Zhou, Global exponential stability of BAM neural networks with distributed delays and impulses, Nonlinear Anal. Real World Appl., 10 (2009), 144-153.