Modeling memory: What do we learn from attractor neural networks?

被引：5
|
作者：
Brunel, N
Nadal, JP
机构：
[1] Ecole Normale Super, Phys Stat Lab, CNRS, URA 1306, F-75231 Paris 05, France
[2] Univ Paris 06, Ecole Normale Super, F-75231 Paris, France
[3] Univ Paris 07, Ecole Normale Super, F-75231 Paris 05, France
来源：
COMPTES RENDUS DE L ACADEMIE DES SCIENCES SERIE III-SCIENCES DE LA VIE-LIFE SCIENCES | 1998年 / 321卷 / 2-3期
关键词：
neural networks; working memory; learning; attractors; spontaneous activity; memory activity;
D O I：
10.1016/S0764-4469(97)89830-7
中图分类号：
Q [生物科学];
学科分类号：
07 ; 0710 ; 09 ;
摘要：
In this paper we summarize some of the main contributions of models of recurrent neural networks with associative memory properties. We compare the behavior of these attractor neural networks with empirical data from both physiology and psychology. This type of network could be used in models with more complex functions. ((C) Academie des sciences/Elsevier, Paris.)
引用
收藏
页码：249 / 252
页数：4
相关论文
共 50 条
12345