Absolute Exponential Stability of Neural Networks with Asymmetric Connection Matrices

Xue-Bin LIANG  Toru YAMAGUCHI  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E80-A   No.8   pp.1531-1534
Publication Date: 1997/08/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8508
Type of Manuscript: LETTER
Category: Neural Networks
Keyword: 
neural networks,  asymmetric connection matrices,  absolute exponential stability time constant,  global exponential convergence rate,  

Full Text: PDF(264KB)>>
Buy this Article




Summary: 
In this letter, the absolute exponential stability result of neural networks with asymmetric connection matrices is obtained, which generalizes the existing one about absolute stability of neural networks, by a new proof approach. It is demonstrated that the network time constant is inversely proportional to the global exponential convergence rate of the network trajectories to the unique equilibrium. A numerical simulation example is also given to illustrate the obtained analysis results.