@book{duda_hart,
author			=		{O. R. Duda  and P. E. Hart. and D. G. Stork},
title			=		{Pattern Classification},
publisher		=		{ John Wiley and Sons, NY},
year			=		{2001}
}	

@conference{reidmiller_backpropagation,
author			=		{M. Riedmiller and H. Braun},
title			=		{A direct adaptive method for faster backpropagation learning: The RPROP algorithm},
booktitle		=		{International Conference on Neural Networks},
year			=		{ 1993},
institution		=		{IEEE}
}

@book{david_mackay,
author			=		{David MacKay},
title			=		{Information Theory, Inference and Learning Algorithms},
year			=		{2003}
}

@book{vapnik_learning,
title			=	{The Nature of Statistical Learning Theory},
author		=	{V. N. Vapnik},
publisher	=	{Springer},
year			=	{1995}
}

@proceeding{shih_bundling,
author		=	{L. Shih and Y D. M. Rennie and Y. Chang and D. R. Karger},
title			=	{Text Bundling: Statistics-based Data Reduction},
booktitle	=	{Twentieth International Conference on Machine Learning (ICML-2003)},
year			=	{2003}
}

@Article{bousquet_stability,
  author = 	 {O. Bousquet and A. Elisseeff},
  title = 	 {Stability and Generalization},
  journal = 	 {Journal of Machine Learning Research},
  year = 	 {2002},
  volume =	 {2},
  pages =	 {499-526},
}


@Article{fleuret_selection,
  author = 	 {F. Fleuret},
  title = 	 {Fast Binary Feature Selection with Conditional Mutual Information},
  journal = 	 {Journal of Machine Learning Research},
  year = 	 {2004},
  key =		 {1531--1555},
  volume =	 {5}
}


@InProceedings{gionis_hashing,
  author = 	 {A. Gionis and P. Indyk and R. Motwani},
  title = 	 {Similarity Search in High Dimensions via Hashing},
  booktitle =	 {25th VLDB Conference},
  year =	 {1999},
}

@Article{guy_review,
  author = 	 {Guyon and Elisseff},
  title = 	 {An introduction to variable and feature selection},
  journal = 	 {Journal of Machine Learning Research},
  year = 	 {2003},
  volume =	 {3},
  pages =	 {1157--1182},
}


@Article{kohavi_john,
  author = 	 {R. Kohavi and G. H. John},
  title = 	 {Wrappers for Feature Subset Selection},
  journal = 	 {Artifical Intelligence},
  year = 	 {1997},
}


@Article{blum_langley,
  author = 	 {A. Blum and P. Langley},
  title = 	 {Selection of relevant features and examples in machine learning},
  journal = 	 {Artifical Intelligence},
  year = 	 {1997},
}



@InProceedings{das_hybrid,
  author = 	 {S. Das},
  title = 	 {Filters, Wrappers and a Boosting based hybrid for feature selection},
  booktitle =	 {ICML},
  year =	 {2001},
}

@Article{stoppigila,
  author = 	 {H. Stoppigilia and G. Dreyfus and R. Dubois and Y. Oussa },
  title = 	 {Ranking a random feature for variable selection},
  journal = 	 {Jounral of Machine Learning Resarch},
  year = 	 {2003},
}


@Article{weston_zero_norm,
  author = 	 {J. Weston and A. Elisseeff and B. Scholkopf },
  title = 	 {Use of zero-norm with linear models and kernel methods},
  journal = 	 {Journal of Machine Learning Research},
  year = 	 {2003},
  volume =	 {3},
  pages =	 {1439--1461},
}

@Book{brieman_cart,
  author = 	 {L. Brieman, J. H. Friedman, R. A. Olshen and C. J. Stone},
  title = 	 {Classification and Regression Trees},
  publisher = 	 {Wadsworth},
  year = 	 {1984},
}

@Article{lecun_obd,
  author = 	 {Y. LeCunn and J. S. Denker and S. A. Solla},
  title = 	 {Optimal Brain Damage},
  journal = 	 {Advances in Neural Information Processing Systems II},
  year = 	 {1990}
}

@Article{quinlan_dt,
  author = 	 {J. R. Quinlan },
  title = 	 {Induction of Decision Trees},
  journal = 	 {Machine Learning},
  year = 	 {1986},
  volume =	 {1},
  pages  =       {81-106}
}