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
收藏
页码：51 / 55
页数：4
相关论文
共 7 条
[1]  
Personnaz L.(1986)Collective computational properties of neural networks: new learning mechanisms Physical Review A 34 4217-4228
[2]  
Guyon I.(1987)Associative recall of memory without errors Physical Review A 35 380-392
[3]  
Dreyfus G.(1993)Attraction radii in binary Hopfield nets are hard to compute Neural Computation 5 812-821
[4]  
Kanter I.(undefined)undefined undefined undefined undefined-undefined
[5]  
Sampolinsky H.(undefined)undefined undefined undefined undefined-undefined
[6]  
Floreen P.(undefined)undefined undefined undefined undefined-undefined
[7]  
Orponen P.(undefined)undefined undefined undefined undefined-undefined
1