| 一种新的双向联想记忆的学习算法 |
| |
| 引用本文： | 修春波,刘向东,张宇河,王帅宇.一种新的双向联想记忆的学习算法[J].小型微型计算机系统,2005,26(6):976-978. |
| |
| 作者姓名： | 修春波 刘向东 张宇河 王帅宇 |
| |
| 作者单位： | 北京理工大学,自动控制系,北京,100081 |
| |
| 基金项目： | 国家自然科学基金(10402003)资助，北京理工大学基础研究基金(BIT-UBF-200301F10)资助 |
| |
| 摘 要： | 提出了一种新的用于双向联想记忆的学习算法，该算法利用了输入向量各元素之间的关联信息，在联想的过程中，动态地调整权值矩阵，增强了网络适应能力，利用了更多的已知信息，从而提高了网络的性能．
|
| 关 键 词： | 神经网络 双向联想记忆 学习算法 |
| 文章编号： | 1000-1220(2005)06-0976-03 |
Novel Learning Algorithm of Bidirectional Associative Memory |
| |
| XIU Chun-bo,LIU Xiang-dong,ZHANG Yu-he,WANG Shuai-Yu.Novel Learning Algorithm of Bidirectional Associative Memory[J].Mini-micro Systems,2005,26(6):976-978. |
| |
| Authors: | XIU Chun-bo LIU Xiang-dong ZHANG Yu-he WANG Shuai-Yu |
| |
| Abstract: | A novel learning algorithm of bidirectional associative memory is proposed in this paper, which makes use of more correlation information than others. The information utilized includes the correlation among the elements of not only the sample patterns, but also the input pattern. The network could adjust the weight matrix dynamically according to the input pattern. All of this improve the adaptability and the performance of the network. |
| |
| Keywords: | neural network bidirectional associative memory learning algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
