Synonyms
Method
Most covering algorithms operate in a concept learning framework, i.e., they assume a set of positive and negative training examples. Adaptations to the multi-class case are typically performed via class binarization, learning different rule sets for binary problems. Some algorithms, most notably CN2 (Clark and Niblett 1989; Clark and Boswell 1991), learn multi-class rules directly by optimizing overall possible classes in the head of the rule. In this case, the resulting theory is interpreted as a decision list. In the following, we will assume a two-class problem with a positive and a negative class.
The Covering algorithm starts with an empty theory. If there are any positive examples in the training set, it calls the subroutine FindBestRulefor learning a single rule that will cover a subset of the positive examples (and possibly some negative examples as well). All covered examples are then separated from the training set, the learned...
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Recommended Reading
Clark P, Boswell R (1991) Rule induction with CN2: some recent improvements. In: Proceedings of the 5th European working session on learning (EWSL-91), Porto. Springer, pp 151–163
Clark P, Niblett T (1989) The CN2 induction algorithm. Mach Learn 3(4):261–283
Cohen WW (1995) Fast effective rule induction. In: Prieditis A, Russell S (eds) Proceedings of the 12th international conference on machine learning (ML-95), Lake Tahoe. Morgan Kaufmann, pp 115–123
Fürnkranz J (1999) Separate-and-conquer rule learning. Artif Intell Rev 13(1):3–54. http://www.ofai.at/cgi-bin/tr-online?number+96-25
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Science+Business Media New York
About this entry
Cite this entry
Fürnkranz, J. (2017). Covering Algorithm. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning and Data Mining. Springer, Boston, MA. https://doi.org/10.1007/978-1-4899-7687-1_275
Download citation
DOI: https://doi.org/10.1007/978-1-4899-7687-1_275
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4899-7685-7
Online ISBN: 978-1-4899-7687-1
eBook Packages: Computer ScienceReference Module Computer Science and Engineering