Semi-Supervised Learning of Mixture Models

Proceedings, Twentieth International Conference on Machine Learning

Volumn 1, Issue , 2003, Pages 99-106

  Cozman, Fabio Gagliardi ^a   Cohen, Ira ^b   Cirelo, Marcelo Cesar ^a  

^a UNIVERSITY OF SÃO PAULO   (Brazil)

^b UNIVERSITY OF ILLINOIS AT URBANA CHAMPAIGN   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DEGRADATION PHENOMENA; SEMI SUPERVISED LEARNING;

COMPUTATION THEORY; COMPUTER SIMULATION; DATA ACQUISITION; ERROR ANALYSIS; MATHEMATICAL TECHNIQUES; THEOREM PROVING;

LEARNING SYSTEMS;

EID: 1942452771     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (36)

1. Baluja, S. (1998). Probabilistic modeling for face orientation discrimination: Learning from labeled and unlabeled data. Neural Information Processing Systems.
2. Berk, R. H. (1966). Limiting behavior of posterior distributions when the model is incorrect. Annals of Math. Statistics, 51-58.
3. Bruce, R. (2001). Semi-supervised learning using prior probabilities and EM. Int. Joint Conf. on Artificial Intelligence Workshop on Text Learning.
4. Castelli, V. (1994). The relative value of labeled and unlabeled samples in pattern recognition. PhD dissertation, Stanford University.
5. Castelli, V., & Cover, T. M. (1995). On the exponential value of labeled samples. Pattern Recognition Letters, 16, 105-111.
6. Castelli, V., & Cover, T. M. (1996). The relative value of labeled and unlabeled samples in pattern recognition with an unknown mixing parameter. IEEE Trans. on Information Theory, 42, 2102-2117.
7. Cohen, I., Sebe, N., Cozman, F. G., Cirelo, M. C., & Huang, T. (2003). Learning Bayesian network classifiers for facial expression recognition using both labeled and unlabeled data. Conf. on Computer Vision and Pattern Recognition (to appear).
8. Collins, M., & Singer, Y. (2000). Unsupervised models for named entity classification. Int. Conf. on Machine Learning (pp. 327-334).
9. Comité, F. D., Denis, F., Gilleron, R., & Letouzey, F. (1999). Positive and unlabeled examples help learning. Int. Conf. on Algorithmic Learning Theory (pp. 219-230). Springer-Verlag.
10. Cooper, D. B., & Freeman, J. H. (1970). On the asymptotic improvement in the outcome of supervised learning provided by additional nonsupervised learning. IEEE Trans. on Computers, C-19, 1055-1063.
11. Corduneanu, A., & Jaakkola, T. (2002). Continuations methods for mixing heterogeneous sources. Conf. on Uncertainty in Artificial Intelligence (pp. 111-118).
12. Cozman, F. G., & Cohen, I. (2002). Unlabeled data can degrade classification performance of generative classifiers. Int. Conf. of the Florida Artificial Intelligence Research Society (pp. 327-331). Pensacola, Florida.
13. Cozman, F. G., & Cohen, I. (2003). The Effect of Modeling Errors in Semi-Supervised Learning of Mixture Models, How Unlabeled Data Can Degrade Performance of Generative Classifiers, at http://www.poli.usp.br/p/fabio.cozman/ Publications/Report/lui.ps.gz.
14. Devroye, L., Gyorfi, L., & Lugosi, G. (1996). A probabilistic theory of pattern recognition. New York: Springer Verlag.
15. Friedman, N., Geiger, D., & Goldszmidt, M. (1997). Bayesian network classifiers. Machine Learning, 29, 131-163.
16. Ganesalingam, S., & McLachlan, G. J. (1978). The efficiency of a linear discriminant function based on unclassified initial samples. Biometrika, 65.
17. Meila, M. (1999). Learning with mixtures of trees. PhD dissertation, MIT.
18. Ghani, R. (2001). Combining labeled and unlabeled data for text classification with a large number of categories. IEEE Int. Conf. on Data Mining.
19. Goldman, S., & Zhou, Y. (2000). Enhancing supervised learning with unlabeled data. Int. Joint Conf. on Machine Learning.
20. Huber, P. J. (1967). The behavior of maximum likelihood estimates under nonstandard conditions. In Fifth Berkeley Symposium in Mathematical Statistics and Probability, 221-233.
21. Jaakkola, T. S., Meila, M., & Jebara, T. (1999). Maximum entropy discrimination. Neural Information Processing Systems 12.
22. Hosmer Jr., D. W. (1973). A comparison of iterative maximum likelihood estimates of the parameters of a mixture of two normal distributions under three different types of sample. Biometrics, 29, 761-770.
23. Kharin, Y. (1996). Robustness in statistical pattern recognition. Kluver Academic Publishers.
24. McCallum, A., & Nigam, K. (1998). Employing EM and pool-based active learning for text classification. Int. Conf. on Machine Learning (pp. 359-367).
25. McLachlan, G. J. (1992). Discriminant analysis and statistical pattern recognition. New York: John Wiley and Sons Inc.
26. McLachlan, G. J., & Basford, K. E. (1988). Mixture models: inference and applications to clustering. New York: Marcel Dekker Inc.
27. Miller, D. J., & Uyar, H. S. (1996). A mixture of experts classifier with learning based on both labelled and unlabelled data. In Neural Information Processing Systems. 571-577.
28. Nigam, K., McCallum, A. K., Thrun, S., & Mitchell, T. (2000). Text classification from labeled and unlabeled documents using EM. Machine Learning, 39, 103-144.
29. Nigam, K. P. (2001). Using unlabeled data to improve text classification (Technical Report CMU-CS-01-126). School of Computer Science, Carnegie Mellon University, Pennsylvania.
30. O'Neill, T. J. (1978). Normal discrimination with unclassified observations. J. of American Statistical Assoc., 75, 821-826.
31. Ratsaby, J., & Venkatesh, S. S. (1995). Learning from a mixture of labeled and unlabeled examples with parametric side information. COLT (pp. 412-417).
32. Seeger, M. (2001). Learning with labeled and unlabeled data (Technical Report). Institute for Adaptive and Neural Computation, University of Edinburgh, Edinburgh, United Kingdom.
33. Shahshahani, B. M., & Landgrebe, D. A. (1994a). Classification of multi-spectral data by joint supervised-unsupervised learning(Technical Report TR-EE 94-1). School of Electrical Engineering, Purdue University, Indiana.
34. Shahshahani, B. M., & Landgrebe, D. A. (1994b). The effect of unlabeled samples in reducing the small sample size problem and mitigating the Hughes phenomenon. IEEE Trans. on Geoscience and Remote Sensing, 32, 1087-1095.
35. White, H. (1982). Maximum likelihood estimation of misspecified models. Econometrica, 50, 1-25.
36. Zhang, T., & Oles, F. (2000). A probability analysis on the value of unlabeled data for classification problems. Int. Joint Conf. on Machine Learning (pp. 1191-1198).