| 基于概率的覆盖算法的模型及仿真研究 |
| |
| 引用本文： | 周瑛,谢阳群,张铃.基于概率的覆盖算法的模型及仿真研究[J].系统仿真学报,2008,20(17). |
| |
| 作者姓名： | 周瑛 谢阳群 张铃 |
| |
| 作者单位： | 1. 安徽大学管理学院,合肥,230039
2. 安徽大学计算机系,合肥,230039 |
| |
| 基金项目： | 国家自然科学基金，国家重点基础研究发展计划(973计划)，安徽大学校科研和教改项目 |
| |
| 摘 要： | 提出的基于概率的覆盖算法--PBcA是一种新的分类算法,它利用学习所得到的样本的概率分布信息,通过投票的方式来决定覆盖边界中样本的类别.从网络结构上看,它是一种混合型的神经网络,由下面三层的前馈网络和上层的反馈网络组成.通过在覆盖中加入一定数量的异类样本和使用概率的方法来扩大覆盖半径,减少拒识的样本数,提高识别率.计算机仿真实验表明,这种方法有效地提高了学习的精度.
|
| 关 键 词： | 构造性学习算法 神经网络 覆盖算法 概率 |
Research on Model and Simulation of Probability-Based Covering Algorithm |
| |
| ZHOU Ying,XIE Yang-qun,ZHANG Ling.Research on Model and Simulation of Probability-Based Covering Algorithm[J].Journal of System Simulation,2008,20(17). |
| |
| Authors: | ZHOU Ying XIE Yang-qun ZHANG Ling |
| |
| Abstract: | Probability-Based Covering Algorithm (PBCA) is a new classify algorithm. It uses the probability of samples and decides the class of the sample in the border of coverage by voting. The network structure of PBCA is a mixed structure composed of feed-forward network and feedback network. The method of adding some samples of different class and enlarging the coverage radius was used to decrease the number of refused samples and improve the rates of recognition. The algorithm is effective in improving the study precision. |
| |
| Keywords: | constructive study algorithm neural networks covering algorithm probability |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
