Browse > Article
http://dx.doi.org/10.5351/KJAS.2008.21.5.825

Semi-Supervised Learning by Gaussian Mixtures  

Choi, Byoung-Jeong (Dept. of Statistics, Korea University)
Chae, Youn-Seok (Consultant, SAS Korea)
Choi, Woo-Young (Consultant, SAS Korea)
Park, Chang-Yi (Dept. of Statistics, University of Seoul)
Koo, Ja-Yong (Dept. of Statistics, Korea University)
Publication Information
The Korean Journal of Applied Statistics / v.21, no.5, 2008 , pp. 825-833 More about this Journal
Abstract
Discriminant analysis based on Gaussian mixture models, an useful tool for multi-class classifications, can be extended to semi-supervised learning. We consider a model selection problem for a Gaussian mixture model in semi-supervised learning. More specifically, we adopt Bayesian information criterion to determine the number of subclasses in the mixture model. Through simulations, we illustrate the usefulness of the criterion.
Keywords
BIC; classification; density estimation; EM algorithm; Gaussian mixture;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Breiman, L., Fredman, J., Olshen, R. and Stone, C. (1984). Classification and Regression Trees, Wadsworth, Belmont
2 Zhu X. (2005). Semi-Supervised Learning Literature Survey, Technical Report 1530, Computer Sciences, University of Wisconsin-Madison
3 Dempster, A. P., Laird, N. M. and Rubin, D. B. (1977). Maximum likelihood from incomplete data via the EM algorithm, Jornal of the Royal Statistical Society, Series B, 39, 1-38
4 Halbe, Z. and Aladjem, M. (2005). Model-based mixture discriminant analysis|an experimental study, Pattern Recognition, 38, 437-440   DOI   ScienceOn
5 Hastie, T. and Tibshirani, R. (1996). Discriminant analysis by Gaussian Mixtures, Journal of the Royal Statististical Society, Serise B, 58, 158-176
6 Nigam, K., McCallum, A. K., Thrun, S. and Mitchell, T. (2000). Text classification from labeled and unlabeled documents using EM, Machine Learning, 39, 103-134   DOI