A Sparse Sampling Method for Classification Based on Likelihood Factor

Authors:
Linge Ding;Fuchun Sun;Hongqiao Wang;Ning Chen
Affiliations:
Department of Computer Science and Technology, State Key Lab of Intelligent Technology and Systems, Tsinghua University, Beijing, China 100084;Department of Computer Science and Technology, State Key Lab of Intelligent Technology and Systems, Tsinghua University, Beijing, China 100084;Department of Computer Science and Technology, State Key Lab of Intelligent Technology and Systems, Tsinghua University, Beijing, China 100084;Department of Computer Science and Technology, State Key Lab of Intelligent Technology and Systems, Tsinghua University, Beijing, China 100084
Venue:
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks, Part II
Year:
2008

Citing 5
Cited 0

The nature of statistical learning theory

The nature of statistical learning theory
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Support Vector Machines and the Bayes Rule in Classification

Data Mining and Knowledge Discovery
Support vector machines are universally consistent

Journal of Complexity
A tutorial on support vector regression

Statistics and Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The disadvantages of large computing and complex discriminant function involved in classical SVM emerged when the scale of training data was larger. In this paper, a method for classification based on sparse sampling is proposed. A likelihood factor which can indicate the importance of sample is defined. According to the likelihood factor, non-important samples are cliped and misjudged samples are revised, this is called sparse sampling. Sparse sampling can reduce the number of the training samples and the number of the support vectors. So the improved classification method has advantages in reducing computational complexity and simplifying discriminant function.