Exponential stability of periodic solutions of recurrent neural networks with functional dependence on piecewise constant argument

Authors

MARAT AKHMET
DUYGU ARUĞASLAN ÇİNÇİN
NUR CENGİZ

DOI

10.3906/mat-1606-138

Abstract

In this study, we develop a model of recurrent neural networks with functional dependence on piecewise constant argument of generalized type. Using the theoretical results obtained for functional differential equations with piecewise constant argument, we investigate conditions for existence and uniqueness of solutions, bounded solutions, and exponential stability of periodic solutions. We provide conditions based on the parameters of the model.

Keywords

Recurrent neural networks, functional differential equations, piecewise constant argument, periodic solution, stability

First Page

272

Last Page

292

Recommended Citation

AKHMET, MARAT; ÇİNÇİN, DUYGU ARUĞASLAN; and CENGİZ, NUR (2018) "Exponential stability of periodic solutions of recurrent neural networks with functional dependence on piecewise constant argument," Turkish Journal of Mathematics: Vol. 42: No. 1, Article 23. https://doi.org/10.3906/mat-1606-138
Available at: https://journals.tubitak.gov.tr/math/vol42/iss1/23