期刊
NEURAL PROCESSING LETTERS
卷 26, 期 1, 页码 1-40出版社
SPRINGER
DOI: 10.1007/s11063-007-9040-2
关键词
bidirectional associative memories; Alpha-Beta associative memories; perfect recall; fingerprint identifier
In this work a new Bidirectional Associative Memory model, surpassing every other past and cuffent model, is presented. This new model is based on Alpha-Beta associative memories, from whom it inherits its name. The main and most important characteristic of Alpha-Beta bidirectional associative memories is that they exhibit perfect recall of all patterns in the fundamental set, without requiring the fulfillment of any condition. The capacity they show is 2(min(n,m)),being n and m the input and output patterns dimensions, respectively. Design and functioning of this model are mathematically founded, thus demonstrating that pattern recall is always perfect, with no regard to the trained pattern characteristics, such as linear independency, orthogonality, or Hamming distance. Two applications illustrating the optimal functioning of the model are shown: a translator and a fingerprint identifier.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据