Increasing and decreasing returns and losses in mutual information feature subset selection
DOI10.3390/E12102144zbMATH Open1229.62005OpenAlexW1983091269MaRDI QIDQ657494FDOQ657494
Marc M. Van Hulle, Gert Van Dijck
Publication date: 9 January 2012
Published in: Entropy (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.3390/e12102144
Recommendations
- Is mutual information adequate for feature selection in regression?
- Subset selection algorithm based on mutual information
- Feature selection using mutual information and neural networks
- Can high-order dependencies improve mutual information based feature selection?
- Feature selection with dynamic mutual information
Bayesian networksconditional entropyconditional mutual informationfeature subset selectionbit paritydecreasing lossesincreasing losses
Statistical aspects of information-theoretic topics (62B10) Bayesian inference (62F15) Theory of languages and software systems (knowledge-based systems, expert systems, etc.) for artificial intelligence (68T35)
Cites Work
- 10.1162/153244303322753616
- Title not available (Why is that?)
- Title not available (Why is that?)
- Computational Methods of Feature Selection
- Relations between entropy and error probability
- Probability of error, equivocation, and the Chernoff bound
- Computer-Automated Design of Multifont Print Recognition Logic
- Efficient selection of discriminative genes from microarray gene expression data for cancer diagnosis
- A Programmed Algorithm for Designing Multifont Character Recognition Logics
Cited In (3)
- Joint Markov blankets in feature sets extracted from wavelet packet decompositions
- Relevance measures for subset variable selection in regression problems based on \(k\)-additive mutual information
- Some convex functions based measures of independence and their application to strange attractor reconstruction
This page was built for publication: Increasing and decreasing returns and losses in mutual information feature subset selection
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q657494)
