Computer Science – Artificial Intelligence
Scientific paper
2002-06-03
Proc. 14th International Conference on Uncertainty in Artificial Intelligence (UAI 2002) pages 577-584
Computer Science
Artificial Intelligence
8 two-column pages
Scientific paper
Mutual information is widely used in artificial intelligence, in a descriptive way, to measure the stochastic dependence of discrete random variables. In order to address questions such as the reliability of the empirical value, one must consider sample-to-population inferential approaches. This paper deals with the distribution of mutual information, as obtained in a Bayesian framework by a second-order Dirichlet prior distribution. The exact analytical expression for the mean and an analytical approximation of the variance are reported. Asymptotic approximations of the distribution are proposed. The results are applied to the problem of selecting features for incremental learning and classification of the naive Bayes classifier. A fast, newly defined method is shown to outperform the traditional approach based on empirical mutual information on a number of real data sets. Finally, a theoretical development is reported that allows one to efficiently extend the above methods to incomplete samples in an easy and effective way.
Hutter Marcus
Zaffalon Marco
No associations
LandOfFree
Robust Feature Selection by Mutual Information Distributions does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Robust Feature Selection by Mutual Information Distributions, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Robust Feature Selection by Mutual Information Distributions will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-693124