Abstract
The upper storage capacity of a neural network for patterns of fixed magnetization m is calculated. The optimal capacity increases with the correlation m2 between the patterns.
Click here to close this panel.
E. Gardner1
Published under licence by IOP Publishing Ltd
,
,
Citation E. Gardner 1987 EPL 4 481
DOI 10.1209/0295-5075/4/4/016
1226 Total downloads
The upper storage capacity of a neural network for patterns of fixed magnetization m is calculated. The optimal capacity increases with the correlation m2 between the patterns.