Global exponential stability of neural networks with non-smooth and impact activations

Date

2012-10-01

Author

Akhmet, Marat

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

171
views

0
downloads

In this paper, we consider a model of impulsive recurrent neural networks with piecewise constant argument. The dynamics are presented by differential equations with discontinuities such as impulses at fixed moments and piecewise constant argument of generalized type. Sufficient conditions ensuring the existence, uniqueness and global exponential stability of the equilibrium point are obtained. By employing Green's function we derive new result of existence of the periodic solution. The global exponential stability of the solution is investigated. Examples with numerical simulations are given to validate the theoretical results.

Subject Keywords

Recurrent neural networks, Impulsive differential equation, Piecewise constant argument, Equilibrium, Periodic solution, Global exponential stability

URI

https://hdl.handle.net/11511/35590

Journal

NEURAL NETWORKS

DOI

https://doi.org/10.1016/j.neunet.2012.06.004

Collections

Department of Mathematics, Article

Suggestions

OpenMETU
Core

Impulsive Hopfield-type neural network system with piecewise constant argument Akhmet, Marat; Yılmaz, Elanur (2010-08-01) In this paper we introduce an impulsive Hopfield-type neural network system with piecewise constant argument of generalized type. Sufficient conditions for the existence of the unique equilibrium are obtained. Existence and uniqueness of solutions of such systems are established. Stability criterion based on linear approximation is proposed. Some sufficient conditions for the existence and stability of periodic solutions are derived. An example with numerical simulations is given to illustrate our results.
Exponential stability of periodic solutions of recurrent neural networks with functional dependence on piecewise constant argument Akhmet, Marat; Cengiz, Nur (null; 2015-08-25) Akhmet [1] generalized differential equations with piecewise constant argument by taking any piecewise constant functions as arguments, and recently he introduced functional dependence on piecewise constant argument [2]. These equations play an important role in applications such as neural networks [3]. In this study, we develope a model of recurrent neural network with functional dependence on piecewise constant argument of generalized type given by x 0 (t) = −Ax (t) + Ex (γ (t)) + Bh (xt) + Cg xγ(t) + D...
Stability analysis of recurrent neural networks with piecewise constant argument of generalized type Akhmet, Marat; Yılmaz, Elanur (2010-09-01) In this paper, we apply the method of Lyapunov functions for differential equations with piecewise constant argument of generalized type to a model of recurrent neural networks (RNNs). The model involves both advanced and delayed arguments. Sufficient conditions are obtained for global exponential stability of the equilibrium point. Examples with numerical simulations are presented to illustrate the results.
Almost periodic solutions of retarded SICNNs with functional response on piecewise constant argument Akhmet, Marat; Kirane, Mokhtar (2016-12-01) We consider a new model for shunting inhibitory cellular neural networks, retarded functional differential equations with piecewise constant argument. The existence and exponential stability of almost periodic solutions are investigated. An illustrative example is provided.
Poisson Stability in Symmetrical Impulsive Shunting Inhibitory Cellular Neural Networks with Generalized Piecewise Constant Argument Akhmet, Marat; Tleubergenova, Madina; Seilova, Roza; Nugayeva, Zakhira (2022-09-01) In the paper, shunting inhibitory cellular neural networks with impulses and the generalized piecewise constant argument are under discussion. The main modeling novelty is that the impulsive part of the systems is symmetrical to the differential part. Moreover, the model depends not only on the continuous time, but also the generalized piecewise constant argument. The process is subdued to Poisson stable inputs, which cause the new type of recurrent signals. The method of included intervals, recently introd...

Citation Formats

M. Akhmet, “Global exponential stability of neural networks with non-smooth and impact activations,” NEURAL NETWORKS, pp. 18–27, 2012, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/35590.