参考:http://scikit-learn.org/stable/modules/manifold.html
1、流形学习是非线性的降维方法(an approach to non-linear dimensionality reduction)。
2、因为随机映射会随机损失数据内部信息;因为类似于PCA、LDA等降维方法基于线性假设,经常会损失数据内部非线性的结构信息;流形学习是线性降维方法的generalization,目的是捕获数据内部非线性的结构。
3、Though supervised variants exist, the typical manifold learning problem is unsupervised: it learns the high-dimensional structure of the data from the data itself, without the use of predetermined classifications.(尽管是监督的变形,但典型的流形学习还是非监督的)
4、sklearn中对流形学习的实现(了解一下就好了。。。。):
1)Isomap algorithm, short for Isometric Mapping(等距映射)。
2)Locally linear embedding (LLE),局部线性嵌入。 seeks a lower-dimensional projection of the data which preserves distances within local neighborhoods,保持局部线性,但整体非线性,相当于一系列的局部PCA组合。
3)Modified Locally linear embedding
4)Hessian Eigenmapping (also known as Hessian-based LLE: HLLE)
5)Spectral Embedding (also known as Laplacian Eigenmaps)
给个参考:http://blog.csdn.net/chl033/article/details/6107042