Abstract
This paper considers the convergence problem of high-order cellular neural networks with delays and oscillating coefficients in leakage terms. Based on a new integral inequality technique, some sufficient conditions are derived to ensure that all solutions of the addressed system converge exponentially to zero vector. Also, two examples and their numerical simulations are given to illustrate the main results.
Similar content being viewed by others
References
Dembo A, Farotimi O, Kailath T (1991) High-order absolutely stable neural networks. IEEE Trans Circuits Syst 38:57–65
Psaltis D, Park CH, Hong J (1988) Higher order associative memories and their optical implementations. Neural Netw 1:143–163
Karayiannis NB, Venetsanopoulos AN (1995) On the training and performance of high-order neural networks. Math Biosci 129(2):143–168
Xu Y (2014) Anti-periodic solutions for HCNNs with time-varying delays in the leakage terms. Neural Comput Appl 24(5):1047–1058
Zhang A (2013) Existence and exponential stability of anti-periodic solutions for HCNNs with time-varying leakage delays. Adv Differ Equ 162:1–14
Jia R, Yang M (2014) Convergence for HRNNs with unbounded activation functions and time-varying delays in the leakage terms. Neural Process Lett 39:69–79
Xiong W (2014) New result on convergence for HCNNs with time-varying leakage delays. Neural Comput Appl. doi:10.1007/s00521-014-1733-7
Chen Z, Yang M (2013) Exponential convergence for HRNNs with continuously distributed delays in the leakage terms. Neural Comput Appl 23:2221–2229
Yu Y, Jiao W (2014) New results on exponential Convergence for HRNNs with continuously distributed delays in the leakage terms. Neural Process Lett 39:167–177
Liu B (2014) Pseudo almost periodic solutions for CNNs with continuously distributed leakage delays. Neural Process Lett. doi:10.1007/s11063-014-9354-9
Liu B (2015) Pseudo almost periodic solutions for neutral type CNNs with continuously distributed leakage delays. Neurocomputing 148:445–454
Berezansky L, Braverman E (2009) On exponential stability of a linear delay differential equation with an oscillating coefficient. Appl Math Lett 22:1833–1837
Jiang A (2015) Exponential convergence for HCNNs with oscillating coefficients in leakage terms. Neural Process Lett. doi:10.1007/s11063-015-9418-5
Jiang A (2015) Exponential convergence for shunting inhibitory cellular neural networks with oscillating coefficients in leakage terms. Neurocomputing. doi:10.1016/j.neucom.2015.03.005
Acknowledgments
The author would like to express the sincere appreciation to the editor and reviewers for their helpful comments in improving the presentation and quality of the paper. In particular, the author expresses the sincere gratitude to Profs. Bingwen Liu and Weizhi Liao for the helpful discussion when this revision work was being carried out.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Liu, X. Improved convergence criteria for HCNNs with delays and oscillating coefficients in leakage terms. Neural Comput & Applic 27, 917–925 (2016). https://doi.org/10.1007/s00521-015-1906-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-015-1906-z