Abstract

Windowing has been proposed as a procedure for efficient memory use in the ID3 decision tree learning algorithm. However, it was shown that it may often lead to a decrease in performance, in particular in noisy domains. Following up on previous work, where we have demonstrated that the ability of rule learning algorithms to learn rules independently can be exploited for more efficient windowing procedures, we demonstrate in this paper how this property can be exploited to achieve noise-tolerance in windowing.

Citations

4072	JR: C4.5: Programs for Machine Learning - Quinlan
2888	Induction of Decision Trees - Quinlan - 1986
800	Fast effective rule induction - Cohen - 1995
682	The CN2 induction algorithm - Clark, Niblett - 1989
292	Learning Efficient Classification Procedures and their Application to Chess End Games - Quinlan - 1983
215	P: From data mining to knowledge discovery in databases (a survey - Fayyad, Piatetsky-Shapiro, et al. - 1996
194	Heterogeneous uncertainty sampling for supervised learning - Lewis, Catlett - 1994
118	Separate-and-Conquer Rule Learning - Fürnkranz - 1999
101	Incremental Reduced Error Pruning - Fürnkranz, Widmer - 1994
56	Megainduction: A test flight - Catlett - 1991
12	Experiments on the costs and benefits of windowing in ID3 - Wirth, Catlett - 1988
5	More efficient windowing - Furnkranz - 1997