Global stability analysis of multitime-scale neural networks

Global asymptotic stability problem is studied for a class of recurrent neural networks with multitime scale. The concerned network involves two coupling terms, i.e., long-term memory and short-term memory, which leads to the difficulty to the dynamics analysis, especially for the case of multiple t...

Full description

Saved in:
Bibliographic Details
Published in:Neural computing & applications 2013-02, Vol.22 (2), p.211-217
Main Authors: Wang, Zhanshan, Zhang, Enlin, Zhang, Huaguang, Ren, Zhengyun
Format: Article
Language:English
Subjects:
Artificial Intelligence
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Data Mining and Knowledge Discovery
Image Processing and Computer Vision
Isnn 2011
Probability and Statistics in Computer Science
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Global asymptotic stability problem is studied for a class of recurrent neural networks with multitime scale. The concerned network involves two coupling terms, i.e., long-term memory and short-term memory, which leads to the difficulty to the dynamics analysis, especially for the case of multiple time varying delays. Some novel stability criteria are proposed on the basis of linear matrix inequality technique for the concerned neural network, which sufficiently consider the inhibitory actions in the different memories. From the viewpoint of biological information, the proposed results obviously improve the existing stability criteria. A numerical example is used to show the effectiveness of the obtained results.
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-011-0680-9