Increasing Attraction of Pseudo-Inverse Autoassociative Networks

被引：8

作者：

Dmitry O. Gorodnichy

Alexandre M. Reznik

机构：

[1] University of Alberta,Department of Computing Science

[2] IPMMS,undefined

[3] Cybernetics Center of Ukrainian Academy of Sciences,undefined

来源：

Neural Processing Letters | 1997年 / 5卷 / 2期

关键词：

attraction radius; pseudo-inverse learning rule; self-connections;

D O I：

10.1023/A:1009614025059

中图分类号：

学科分类号：

摘要：

We show how partial reduction of self-connections of the network designed with the pseudo-inverse learning rule increases the direct attraction radius of the network. Theoretical formula is obtained. Data obtained by simulation are presented.

引用

页码：51 / 55

页数：4