Stability and statistical properties of second-order bidirectional associative memory

被引:20
|
作者
Leung, CS [1 ]
Chan, LW [1 ]
Lai, EMK [1 ]
机构
[1] EDITH COWAN UNIV,DEPT COMP & COMMUN ENGN,PERTH,WA,AUSTRALIA
来源
关键词
associative memory; BAM; neural network; stability;
D O I
10.1109/72.557664
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, a bidirectional associative memory (BAM) model with second-order connections, namely second-order bidirectional associative memory (SOBAM), is first reviewed, The stability and statistical properties of the SOBAM are then examined, We use an example to illustrate that the stability of the SOBAM is not guaranteed, For this result, we cannot use the conventional energy approach to estimate its memory capacity, Thus, we develop the statistical dynamics of the SOBAM, Given that a small number of errors appear in the initial input, the dynamics shows how the number of errors varies during recall, We use the dynamics to estimate the memory capacity, the attraction basin, and the number of errors in the retrieved items, Extension of the results to higher-order bidirectional associative memories is also discussed.
引用
收藏
页码:267 / 277
页数:11
相关论文
共 50 条