| 双向联想记忆神经网络的一种编码策略 |
| |
| 引用本文： | 于海斌,徐心和.双向联想记忆神经网络的一种编码策略[J].电子学报,1997,25(5):6-10. |
| |
| 作者姓名： | 于海斌 徐心和 |
| |
| 作者单位： | [1]中科院沈阳自动化所 [2]东北大学控制仿真中心 |
| |
| 基金项目： | 国家高技术863计划资助 |
| |
| 摘 要： | 本文提出一种双向联想记忆神经网络的按‘位’加权编码策略，并给出了求取权值递推算法，它将Ｋｏｓｋｏ双向联想记忆网络按海明距离进行模式匹配的原则，修正了按加权海明距离进行了模式匹配，从而可以使得对不满足加续性的所谓“病态结构”的一类样本模式集，同样具有良好的联想能力，对二值图象模式存贮，联想的计算机模拟实验表明，此方法具有优良的性能和实用价值。
|
| 关 键 词： | 神经网络 双向联想记忆 海明距离 最速下降法 |
A New Coding Strategy for Bidirectional Associative Memories |
| |
| Abstract: | A coding strategy by weighted bits and a recursive algorithm of obtaining theweights for bidirectional associative memories are presented in the paper. This strategy modifiesKosko's bidirectional associative memories matching patterns by Hamming distance into those byweighted Hamming distance so that ill structured sample pattern set without continuity can also bestored well. It is manifested that this method has high performance and practicability through storing and associating binary pixel patterns with computer simulations. |
| |
| Keywords: | Neural network Bidirectional associative memories Hamming distance Steepest descent algorithm |
| 本文献已被 CNKI 维普 等数据库收录！ |
