DocumentCode
2339389
Title
On the domain of attraction and convergence rate of Hopfield continuous feedback neural networks
Author
Cao, Jinde
Author_Institution
Dept. of Appl. Math., Southeast Univ., Nanjing, China
Volume
5
fYear
2000
fDate
2000
Firstpage
3277
Abstract
The domain of attraction of memory patterns and exponential convergence rate of the network trajectories to memory patterns for Hopfield continuous associative memory are estimated by means of a matrix measure and a comparison principle. These results can be used for the evaluation of fault-tolerance capability and the synthesis procedures for Hopfield continuous feedback associative memory neural networks
Keywords
Hopfield neural nets; content-addressable storage; convergence; fault tolerant computing; feedback; Hopfield continuous associative memory; Hopfield continuous feedback neural networks; comparison principle; domain of attraction; exponential convergence rate; fault-tolerance capability; matrix measure; memory patterns; network trajectories; synthesis procedures; Associative memory; Convergence; Differential equations; Fault tolerance; Hopfield neural networks; Mathematics; Network synthesis; Neural networks; Neurofeedback; State feedback;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Control and Automation, 2000. Proceedings of the 3rd World Congress on
Conference_Location
Hefei
Print_ISBN
0-7803-5995-X
Type
conf
DOI
10.1109/WCICA.2000.863131
Filename
863131
Link To Document