DocumentCode
940492
Title
Information capacity of the Hopfield model
Author
Abu-Mostafa, Yaser S. ; Jacques, Jeannine-marie St
Volume
31
Issue
4
fYear
1985
fDate
7/1/1985 12:00:00 AM
Firstpage
461
Lastpage
464
Abstract
The information capacity of general forms of memory is formalized. The number of bits of information that can be stored in the Hopfield model of associative memory is estimated. It is found that the asymptotic information capacity of a Hopfield network of 
neurons is of the order 
b. The number of arbitrary state vectors that can be made stable in a Hopfield network of neurons is proved to be bounded above by .
neurons is of the order b. The number of arbitrary state vectors that can be made stable in a Hopfield network of neurons is proved to be bounded above by .Keywords
Associative memory; Biological information theory; Biological system modeling; Biology computing; Flexible structures; Hopfield neural networks; Neural networks; Neurons; Robustness; Upper bound;
fLanguage
English
Journal_Title
Information Theory, IEEE Transactions on
Publisher
ieee
ISSN
0018-9448
Type
jour
DOI
10.1109/TIT.1985.1057069
Filename
1057069
Link To Document