Title :
Mining Predictive k-CNF Expressions
Author :
Dries, Anton ; De Raedt, Luc ; Nijssen, Siegfried
Author_Institution :
Dept. of Comput. Sci., Katholieke Univ. Leuven, Leuven, Belgium
fDate :
5/1/2010 12:00:00 AM
Abstract :
We adapt Mitchell´s version space algorithm for mining k-CNF formulas. Advantages of this algorithm are that it runs in a single pass over the data, is conceptually simple, can be used for missing value prediction, and has interesting theoretical properties, while an empirical evaluation on classification tasks yields competitive predictive results.
Keywords :
Boolean functions; data mining; pattern classification; Boolean functions; Mitchell version space algorithm; conjunctive normal form; data mining; k-CNF formulas; missing value prediction; predictive k-CNF expressions mining; rule-based classification; Concept learning; data mining.; machine learning;
Journal_Title :
Knowledge and Data Engineering, IEEE Transactions on
DOI :
10.1109/TKDE.2009.152
