| 一种加权的构造型神经网络覆盖算法设计与实现 |
| |
| 引用本文： | 张晻,张铃,程家兴.一种加权的构造型神经网络覆盖算法设计与实现[J].计算机工程,2005,31(2):36-38. |
| |
| 作者姓名： | 张晻 张铃 程家兴 |
| |
| 作者单位： | 1. 解放军电子工程学院204研究室,合肥,230037;教育部安徽大学人工智能与信号处理重点实验室,合肥,230039
2. 教育部安徽大学人工智能与信号处理重点实验室,合肥,230039 |
| |
| 基金项目： | 国家自然科学基金资助项目(60175018)，国家自然科学基金对外合作项目资助(60111120662) |
| |
| 摘 要： | 在分析覆盖算法的基础上提出了一种加权的覆盖领域算法，在构造神经网络覆盖领域时，充分利用了样本在球形领域间的分布位置特性及分布概率特性，做到真正意义上利用样本特征来构造覆盖神经网络，给出加权覆盖算法的构造方法及步骤，并通过实例进行了验证。
|
| 关 键 词： | 覆盖算法 构造型神经网络 加权 验证 领域 设计 球形 构造方法 样本 步骤 |
| 文章编号： | 1000-3428(2005)02-0036-03 |
Design and Implementation of a Weighted Covering Algorithm for Constructing Neural Networks |
| |
| ZHANG Min,ZHANG Lin,CHENG Jiaxing.Design and Implementation of a Weighted Covering Algorithm for Constructing Neural Networks[J].Computer Engineering,2005,31(2):36-38. |
| |
| Authors: | ZHANG Min ZHANG Lin CHENG Jiaxing |
| |
| Affiliation: | ZHANG Min1,2,ZHANG Lin2,CHENG Jiaxing2 |
| |
| Abstract: | After analyzing the covering algorithm, a weighted covering algorithm is introduced in this paper. By this way, when constructing covering neighborhood of neural networks, not only the characteristics of the position of the training samples on the sphere are used, but also the distribution probability of the samples on the sphere are taken into consideration, which make full use of the learning instances to construct the covering neural network. In this paper, the method and procedures of constructing the weighting covering algorithm are given, and effect of the method is validated through experiment. |
| |
| Keywords: | Neural networks Covering algorithm Weight coefficient |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
