(Enter summary)
Abstract: In this paper, we examine a method for feature subset selection based on Information
Theory. Initially, a framework for defining the theoretically optimal, but computationally intractable,
method for feature subset selection is presented. We show that our goal should be to
eliminate a feature if it gives us little or no additional information beyond that subsumed by
the remaining features. In particular, this will be the case for both irrelevant and redundant
features. We then give an efficient ... (Update)
Cited by: More
Efficient Case Based Feature Construction for Heterogeneous.. - Mierswa, Wurst (2005)
(Correct)
Efficient Feature Construction by Meta Learning - Guiding the .. - Mierswa, Wurst (2005)
(Correct)
Bayesian Graphical Models for Adaptive Filtering - Zhang (2005)
(Correct)
Similar documents (at the sentence level):
70.6%: Toward Optimal Feature Selection - Koller, Sahami (1996)
(Correct)
27.8%: Using Machine Learning To Improve Information Access - Sahami (1999)
(Correct)
Active bibliography (related documents): More All
0.2: A Roadmap to Research on Bayesian Networks and other.. - Chrisman (1998)
(Correct)
0.1: Parallel Probabilistic Inference on Cache-coherent.. - Kozlov, Singh (1996)
(Correct)
0.1: Computational complexity reduction for BN2O networks using.. - Alexander Kozlov
(Correct)
Similar documents based on text: More All
0.2: Hierarchically Classifying Documents Using Very Few Words - Koller, Sahami (1997)
(Correct)
0.2: Using Feature Selection to Find Inputs that Work Better as.. - Caruana, de Sa (1998)
(Correct)
0.1: The Effect of Using Hierarchical Classifiers in Text.. - D'Alessio, Murray.. (2000)
(Correct)
Related documents from co-citation: More All
32: Irrelevant Features and the Subset Selection Problem
- John, Kohavi et al. - 1994
25: Programs for machine learning (context) - Quinlan - 1993
23: Elements of Information Theory (context) - Cover, Thomas - 1991
BibTeX entry: (Update)
Koller, D., & Sahami, M. (1996). Toward Optimal Feature Selection. In: Machine Learning: Proceedings of the Thirteenth International Conference. Morgan Kaufmann. http://citeseer.comp.nus.edu.sg/117819.html More
@misc{ koller96toward,
author = "D. Koller and M. Sahami",
title = "Toward Optimal Feature Selection",
text = "Koller, D., & Sahami, M. (1996). Toward Optimal Feature Selection. In:
Machine Learning: Proceedings of the Thirteenth International Conference.
Morgan Kaufmann.",
year = "1996",
url = "citeseer.comp.nus.edu.sg/117819.html" }
Citations (may not include all citations):
2319
Elements of Information Theory (context) - Cover, Thomas - 1991
2177
Programs for Machine Learning (context) - Quinlan - 1993
2133
Pattern Classification and Scene Analysis (context) - Duda, Hart - 1973
760
Probabilistic Reasoning in Intelligent Systems (context) - Pearl - 1988
667
UCI repository of machine learning databases (context) - Murphy, Aha - 1995
291
Irrelevant features and the subset selection problem
- John, Kohavi et al. - 1994
125
Learning with many irrelevant features
- Almuallim, Dietterich - 1991
121
An analysis of bayesian classifiers
- Langley, Iba et al. - 1992
120
Greedy attribute selection
- Caruana, Freitag - 1994
116
On information and sufficiency (context) - Kullback, Leibler - 1951
111
The feature selection problem: Traditional methods and a new.. (context) - Kira, Rendell - 1992
96
Occam's razor (context) - Blumer, Ehrenfeucht et al. - 1987
80
Induction of selective bayesian classifiers
- Langley, Sage - 1994
51
Wrappers for Performance Enhancement and Oblivious Decision ..
- Kohavi - 1995
27
Efficient learning of selective bayesian network classifiers
- Singh, Provan - 1996
25
Localized partial evaluation of belief networks
- Draper, Hanks - 1994
6
Sensitivities: An alternative to conditional probabilities f..
- Kozlov, Singh - 1995
The graph only includes citing articles where the year of publication is known.
Online articles have much greater impact More about CiteSeer.IST at NUS Add search form to your site Submit documents Feedback
CiteSeer.IST at NUS - Copyright Penn State and NEC. Hosted by the School of Computing, National University of Singapore.