In this paper, global exponential stability in Lagrange sense is further studied for various continuous-time delayed recurrent neural network with two different types of activation functions. Based on the parameters of the systems, detailed estimation of global exponential attractive sets and positive invariant sets are presented without any hypothesis on the existence. It is also verified that outside the global exponential attracting set; i.e., within the global attraction domain, there is no equilibrium state, periodic state, almost periodic state, and chaos attractor of the neural network. These theoretical analysis narrows the search field of optimization computation, associative memories, chaos control and synchronization and provide convenience for applications.
Beschreibung
ScienceDirect - Neurocomputing : Positive invariant and global exponential attractive sets of neural networks with time-varying delays
Neural Networks: Algorithms and Applications, 4th International Symposium on Neural Networks; 50 Years of Artificial Intelligence: a Neuronal Approach, Campus Multidisciplinary in Perception and Intelligence
%0 Journal Article
%1 keyhere
%A Liao, Xiaoxin
%A Luo, Qi
%A Zeng, Zhigang
%B Neural Networks: Algorithms and Applications, 4th International Symposium on Neural Networks; 50 Years of Artificial Intelligence: a Neuronal Approach, Campus Multidisciplinary in Perception and Intelligence
%D 2008
%J Neurocomputing
%K Globally Lagrange Neural Positive attractive exponentially invariant networks set stability
%N 4-6
%P 513--518
%T Positive invariant and global exponential attractive sets of neural networks with time-varying delays
%U http://www.sciencedirect.com/science/article/B6V10-4PT294K-7/2/ea84921486566ffe810bafb26c22a411
%V 71
%X In this paper, global exponential stability in Lagrange sense is further studied for various continuous-time delayed recurrent neural network with two different types of activation functions. Based on the parameters of the systems, detailed estimation of global exponential attractive sets and positive invariant sets are presented without any hypothesis on the existence. It is also verified that outside the global exponential attracting set; i.e., within the global attraction domain, there is no equilibrium state, periodic state, almost periodic state, and chaos attractor of the neural network. These theoretical analysis narrows the search field of optimization computation, associative memories, chaos control and synchronization and provide convenience for applications.
@article{keyhere,
abstract = {In this paper, global exponential stability in Lagrange sense is further studied for various continuous-time delayed recurrent neural network with two different types of activation functions. Based on the parameters of the systems, detailed estimation of global exponential attractive sets and positive invariant sets are presented without any hypothesis on the existence. It is also verified that outside the global exponential attracting set; i.e., within the global attraction domain, there is no equilibrium state, periodic state, almost periodic state, and chaos attractor of the neural network. These theoretical analysis narrows the search field of optimization computation, associative memories, chaos control and synchronization and provide convenience for applications.},
added-at = {2008-02-29T11:34:11.000+0100},
author = {Liao, Xiaoxin and Luo, Qi and Zeng, Zhigang},
biburl = {https://www.bibsonomy.org/bibtex/2de0fecb09efd23305b182d36cf5c8806/pagutierrez},
booktitle = {Neural Networks: Algorithms and Applications, 4th International Symposium on Neural Networks; 50 Years of Artificial Intelligence: a Neuronal Approach, Campus Multidisciplinary in Perception and Intelligence},
description = {ScienceDirect - Neurocomputing : Positive invariant and global exponential attractive sets of neural networks with time-varying delays},
interhash = {2bb195452ea3cc7ec0d92d9b3ed8b235},
intrahash = {de0fecb09efd23305b182d36cf5c8806},
journal = {Neurocomputing},
keywords = {Globally Lagrange Neural Positive attractive exponentially invariant networks set stability},
month = {#jan#},
number = {4-6},
pages = {513--518},
timestamp = {2008-02-29T11:34:12.000+0100},
title = {Positive invariant and global exponential attractive sets of neural networks with time-varying delays},
url = {http://www.sciencedirect.com/science/article/B6V10-4PT294K-7/2/ea84921486566ffe810bafb26c22a411},
volume = 71,
year = 2008
}