UT ML Group: Publication: Ensemble Learning

Ensemble Learning combines multiple learned models under the assumption that "two (or more) heads are better than one." The decisions of multiple hypotheses are combined in ensemble learning to produce more accurate results. Boosting and bagging are two popular approaches. Our work focuses on building diverse committees that are more effective than those built by existing methods, and, in particular, are useful for active learning.

For a general, popular book on the utility of combining diverse, independent opinions in human decision-making, see The Wisdom of Crowds.

Publications

  1. Creating Diverse Ensemble Classifiers to Reduce Supervision [Abstract] [PDF]
    Prem Melville
    Ph.D. Thesis, Department of Computer Sciences, University of Texas at Austin, November 2005.
    141 pages
    Also appears as Technical Report TR-05-49, Artificial Intelligence Lab, University of Texas at Austin, December 2005.

  2. Combining Bias and Variance Reduction Techniques for Regression [Abstract] [PDF]
    Yuk Lai Suen, Prem Melville and Raymond J. Mooney
    Technical Report UT-AI-TR-05-321, Artificial Intelligence Lab, University of Texas at Austin, July 2005.

  3. Combining Bias and Variance Reduction Techniques for Regression [Abstract] [PDF]
    Suen, Y. L., Melville, P., and Mooney, R.J.
    Proceedings of the 16th European Conference on Machine Learning, Porto, Portugal, pp. 741-749, October 2005.

  4. Diverse Ensembles for Active Learning [Abstract] [PDF]
    Prem Melville and Raymond J. Mooney
    Proceedings of the 21st International Conference on Machine Learning (ICML-2004), pp. 584-591, Banff, Canada, July 2004.

  5. Experiments on Ensembles with Missing and Noisy Data [Abstract] [PDF]
    Prem Melville, Nishit Shah, Lilyana Mihalkova, and Raymond J. Mooney
    Proceedings of the Fifth International Workshop on Multiple Classifier Systems (MCS-2004), F. Roli, J. Kittler, and T. Windeatt (Eds.), Lecture Notes in Computer Science, Vol. 3077, pp. 293-302, Cagliari, Italy, Springer Verlag, June 2004.

  6. Creating Diversity in Ensembles Using Artificial Data [Abstract] [PDF]
    Prem Melville and Raymond J. Mooney
    Journal of Information Fusion (Special Issue on Diversity in Multiple Classifier Systems), Vol 6/1 pp 99-111, 2004.

  7. Creating Diverse Ensemble Classifiers [Abstract] [PDF]
    Prem Melville
    Ph.D. proposal, Department of Computer Sciences, University of Texas at Austin, October 2003.
    54 pages.
    Also appears as Technical Report UT-AI-TR-03-306, Artificial Intelligence Lab, University of Texas at Austin, December 2003.

  8. Constructing Diverse Classifier Ensembles Using Artificial Training Examples [Abstract] [PDF]
    Prem Melville and Raymond J. Mooney
    Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI-03), pp. 505-510, Acapulco, Mexico, August 2003.

mooney@cs.utexas.edu