Post-processing operators for decision lists
María A. Franco, Natalio Krasnogor, Jaume Bacardit · 2012
This paper proposes three post-processing operators (rule cleaning, rule pruning and rule swapping) which combined together in different ways can help reduce the complexity of decision lists evolved by means of genetics-based machine learning. While the first two operators work on the independent rules to reduce the number of expressed attributes, the last one changes the order of the rules (based on the similarities between them) to identify and delete the unnecessary ones. These operators were tested using the BioHEL system over 35 different problems. Our results show that it is possible to reduce the number of specified attributes per rule and the number rules up to 30% in some problems, without producing significant changes in the test accuracy. Moreover, the approaches presented in this paper can be easily extended to other learning paradigms and representations.