分类问题的一种流形学习算法

被引:4
作者
姚力群 [1 ]
陶卿 [2 ]
机构
[1] 中国科学院自动化研究所复杂系统与智能科学重点实验室
[2] 炮兵学院
关键词
流形; 局部线性嵌入; 分类问题; 支持向量机;
D O I
暂无
中图分类号
TP181 [自动推理、机器学习];
学科分类号
摘要
提出了一种分类问题的流形学习算法。利用LIE算法的思想寻找样本的内在流形分布,并通过比较未知样本与正样本流形及负样本流形之间的距离来判定该样本的类别。实验显示,本文提出的流形学习算法的分类效果与SVM、Boosting等当前流行的机器学习算法相当。与此同时,该算法具有参数估计简单、参数影响不大等优点,该算法为分类问题的机器学习提供了一条新的途径。
引用
收藏
页码:541 / 545
页数:5
相关论文
共 8 条
  • [1] An introduction to support vector machines and other kernel-based learning methods. Cristianini N,Shawe-Taylor J. . 2000
  • [2] Statistical Learning Theory. Vapnik V N. . 1998
  • [3] The Nature of Statistical Learning Theory. Vapnik V. . 1995
  • [4] Ranking on Data Manifolds. Zhou D,Weston J,Gretton A,Bousquet O,Schlkopf B. Advances in Neural Information Processing Systems . 2003
  • [5] An Introduction to Locally Linear Embedding. Saul L K,,Roweis S T. Journal of Machine Learning Research . 2003
  • [6] A Kernel View of the Dimensionality Reduction of Manifolds. Ham J,Lee D D,Mika S,Schlkopf B. Proc of the 21st International Conference on Machine Learning . 2004
  • [7] Theoretical Views of Boosting and Applications. Schapire R E. Proc of the 10th International Conference on Algorithmic Learning Theory . 1999
  • [8] Nonlinear dimensionality reduction by locally linear embedding. Roweis ST,Saul LK. Science . 2000