日本神経回路学会誌
Online ISSN : 1883-0455
Print ISSN : 1340-766X
ISSN-L : 1340-766X
研究論文
非単調ニューロンを用いて相関学習された連想記憶モデルのS/N解析
木本 智幸小泉 耕二岡田 真人
著者情報
ジャーナル フリー

2001 年 8 巻 3 号 p. 86-93

詳細
抄録
An associative memory model based on the correlation method using a non-monotonic neuron property is proposed and investigated by signal-to-noise analysis. The signal term for recalling and the cross-talk noise term preventing recalling are negatively correlated with each other in this model, so that the variance of the internal potential becomes much smaller than that of the cross-talk noise. This is contrasted with the situation of the Hopfield model in which the two terms are independent of each other. As a result, the present model has twice larger storage capacity in comparison with the Hopfiled model.
著者関連情報
© 2001 日本神経回路学会
前の記事 次の記事
feedback
Top