Guaranteed recall of all training pairs for exponential bidirectional associative memory
Guaranteed recall of all training pairs for exponential bidirectional associative memory
复制标题
保证召回所有训练对以实现指数双向联想记忆
DOI：
10.1049/el:20010115
复制
发表时间：
2001
影响因子：
1.1
通讯作者：
Jujang Lee
中科院分区：
文献类型：
--
作者：
T. Eom;Sang;Jujang Lee
提出了几种保证指数双向联想记忆的所有训练对的回忆的方法。如果模式之间的最小汉明距离已知，则可以确定基数以提供一定的吸引盆。否则可以应用统计最小距离。还开发了基于伪松弛算法的权重学习算法，以使所有训练对都可以用小基数调用。
Several methods of guaranteeing the recall of all training pairs for exponential bidirectional associative memory are presented. If the minimum Hamming distance between patterns is known, the radix can be determined to provide a certain basin of attraction. Otherwise the statistical minimum distance can be applied. A weight learning algorithm based on a pseudo-relaxation algorithm is also developed to make all training pairs recallable with a small radix.