In this paper we use genetic programming for changing the representation of the input data for machine learners. In particular, the topic of interest is here feature construction in the learning-from-examples paradigm, where new features are built based on the original set of attributes. The paper first introduces the general framework for GP-based feature construction. Then, an extended approach is proposed where the useful components of representation (features) are preserved during an evolutionary run, as opposed to the standard approach where valuable features are often lost during search. Finally, we present and discuss the results of an extensive computational experiment carried out on several reference data sets. The outcomes show that classifiers induced using the representation enriched by the GP-constructed features provide better accuracy of classification on the test set. In particular, the extended approach proposed in the paper proved to be able to outperform the standard approach on some benchmark problems on a statistically significant level.
@ARTICLE { Krawiec02,
ABSTRACT = { In this paper we use genetic programming for changing the representation of the input data for machine learners. In particular, the topic of interest is here feature construction in the learning-from-examples paradigm, where new features are built based on the original set of attributes. The paper first introduces the general framework for GP-based feature construction. Then, an extended approach is proposed where the useful components of representation (features) are preserved during an evolutionary run, as opposed to the standard approach where valuable features are often lost during search. Finally, we present and discuss the results of an extensive computational experiment carried out on several reference data sets. The outcomes show that classifiers induced using the representation enriched by the GP-constructed features provide better accuracy of classification on the test set. In particular, the extended approach proposed in the paper proved to be able to outperform the standard approach on some benchmark problems on a statistically significant level. },
AUTHOR = { K. Krawiec },
JOURNAL = { Genetic Programming and Evolvable Machines },
PAGES = { 329--343 },
TITLE = { Genetic Programming-based Construction of Features for Machine Learning and Knowledge Discovery Tasks },
VOLUME = { 4 },
YEAR = { 2002 },
}