Issue No. 05 - May (2010 vol. 22)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TKDE.2009.152
Anton Dries , Katholieke Universiteit Leuven, Leuven
Luc De Raedt , Katholieke Universiteit Leuven, Leuven
Siegfried Nijssen , Katholieke Universiteit Leuven, Leuven
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.
Concept learning, machine learning, data mining.
A. Dries, S. Nijssen and L. De Raedt, "Mining Predictive k-CNF Expressions," in IEEE Transactions on Knowledge & Data Engineering, vol. 22, no. , pp. 743-748, 2009.