流形学习研究综述
首发时间:2005-12-12
摘要:流形学习一般是指一类无监督统计学习问题,其主要目标是发现嵌入在高维数据空间的低维光滑流形。本文着重介绍了流形学习的研究背景、研究动机以及一些有代表性的学习算法,并对进一步的研究作了展望。
关键词: 流形学习 固有维数 Isomap LLE 坐标图卡 特征映射
For information in English, please click here
A Survey on Manifold Learning
Abstract:In the problem of manifold learning, one seeks to find a smooth low dimensional manifold embedded in the high-dimensional linear vector space, based on a set of sample points. In this paper, we focus on the introduction of the background, motivated and some typical algorithms about manifold learning. Finally, we suggest some directions for further research
Keywords: Manifold Learning Intrinsic Dimensionality Isomap LLE Chart Eigenmaps
论文图表:
引用
No.4251406391134353****
同行评议
共计0人参与
勘误表
流形学习研究综述
评论
全部评论0/1000