Absolute Exponential Stability of Neural Networks with Asymmetric Connection Matrices
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.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E80-A No.8 pp.1531-1534
- Publication Date
- 1997/08/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Category
- Neural Networks
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Xue-Bin LIANG, Toru YAMAGUCHI, "Absolute Exponential Stability of Neural Networks with Asymmetric Connection Matrices" in IEICE TRANSACTIONS on Fundamentals,
vol. E80-A, no. 8, pp. 1531-1534, August 1997, doi: .
Abstract: 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.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e80-a_8_1531/_p
Copy
@ARTICLE{e80-a_8_1531,
author={Xue-Bin LIANG, Toru YAMAGUCHI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Absolute Exponential Stability of Neural Networks with Asymmetric Connection Matrices},
year={1997},
volume={E80-A},
number={8},
pages={1531-1534},
abstract={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.},
keywords={},
doi={},
ISSN={},
month={August},}
Copy
TY - JOUR
TI - Absolute Exponential Stability of Neural Networks with Asymmetric Connection Matrices
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1531
EP - 1534
AU - Xue-Bin LIANG
AU - Toru YAMAGUCHI
PY - 1997
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E80-A
IS - 8
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - August 1997
AB - 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.
ER -
English
