流形学习中非线性维数约简方法概述  

Overview of nonlinear dimensionality reduction methods in manifold learning

作　　者：黄启宏[1] 刘钊[1] 

机构地区：[1]电子科技大学电子工程学院,成都610054

出　　处：《计算机应用研究》2007年第11期19-25,共7页Application Research of Computers

摘　　要：较为详细地回顾了流形学习中非线性维数约简方法,分析了它们各自的优势和不足。与传统的线性维数约简方法相比较,可以发现非线性高维数据的本质维数,有利于进行维数约简和数据分析。最后展望了流形学习中非线性维数方法的未来研究方向,期望进一步拓展流形学习的应用领域。A detailed retrospection was made on nonlinear dimensionality reduction methods in manifold learning, whose advantages and defects were pointed out respectively. Compared with traditional linear method, nonlinear dimensionality reduction methods in manifold learning could discover the intrinsic dimensions of nonlinear high-dimensional data effectively, help researcher to reduce dimensionality and analyzer data better, Finally, the prospect of nonlinear dimensionality reduction methods in manifold learning was discussed, so as to extend the application area of manifold learning.

关 键 词：维数约简 流形学习 多维尺度 等距映射 拉普拉斯特征映射 局部线性嵌入 局部切空间排列 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]