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.
出处
《计算机应用研究》
CSCD
北大核心
2007年第11期19-25,共7页
Application Research of Computers
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
dimensional reduction
manifold learning
multidimensional sealing ( MDS )
isomap
Laplaeian eigenmap
locally linear embedding( LLE )
local tangent space alignment(LTSA)