| 全局保持的流形学习算法对比研究 |
| |
| 引用本文： | 曾宪华,罗四维.全局保持的流形学习算法对比研究[J].计算机工程与应用,2010,46(15):1-6. |
| |
| 作者姓名： | 曾宪华 罗四维 |
| |
| 作者单位： | 1. 重庆邮电大学计算机科学与技术研究所,重庆,400065
2. 北京交通大学计算机与信息技术学院,北京,100044 |
| |
| 基金项目： | 国家自然科学基金No.60773016;;重庆邮电大学博士启动基金项目(No.A2009-24)~~ |
| |
| 摘 要： | 全局保持的流形学习算法主要是基于保持高维观测空间和内在低维流形的全局几何特性。详细比较了全局保持的典型流形学习算法的特点及其相互之间的联系，标明了它们的优点与缺陷。实验说明这些方法发现的内在维数和内在低维流形的差异。最后提出了一些新的流形学习研究方向。
|
| 关 键 词： | 全局保持 谱方法 核主成分分析 等度规映射 最大方差展开 |
| 收稿时间： | 2009-12-1 |
| 修稿时间： | 2010-3-17
|
Contrasting research of global preserving manifold learning algorithms |
| |
| ZENG Xian-hua,LUO Si-wei.Contrasting research of global preserving manifold learning algorithms[J].Computer Engineering and Applications,2010,46(15):1-6. |
| |
| Authors: | ZENG Xian-hua LUO Si-wei |
| |
| Affiliation: | 1.Institute of Science ＆ Technology of Computer,Chongqing University of Posts and Telecommunications,Chongqing 400065,China 2.School of Computer and Information Technology,Beijing Jiaotong University,Beijing 100044,China |
| |
| Abstract: | Global preserving manifold learning algorithms are mainly based on preserving global geometric properties between high-dimensional observed space and intrinsic low-dimensional manifold.This paper compares in detail the characters and interre-lations of several classical manifold learning algorithms based on preserving global properties.Some advantages and shortcomings of these algorithms are shown.Experimental results demonstrate the differences of these algorithms about intrinsic dimension and intrinsic lo... |
| |
| Keywords: | global preserving spectral method kernel Principal Components Analysis ISOmetric MAPping Maximum Variance Unfolding |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载全文 |
