Increasing attraction of pseudo-inverse autoassociative networks
Increasing attraction of pseudo-inverse autoassociative networks
复制标题
DOI：
10.1023/a:1009614025059
复制
发表时间：
1997-04-01
影响因子：
3.1
通讯作者：
Reznik, AM
中科院分区：
文献类型：
--
作者：
Gorodnichy, DO;Reznik, AM
我们证明了用伪逆学习规则设计的网络的自连接的部分减少增加了网络的直接吸引半径。得到了理论公式。通过模拟获得的数据。
We show howl 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.