Abstract
Identifying a good set of features is critical to the performance of learning algorithms such as classifiers. Previous methods have focused on either selecting a subset of features or transforming features using principle components analysis. In this paper, we propose a genetic algorithm approach that searches for a good feature transformation function over a subset of features using a novel representation scheme with novel reproduction operators. Preliminary experimental results using the UCI data set show promising results.
Original language | English (US) |
---|---|
Title of host publication | Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication |
Pages | 2061-2062 |
Number of pages | 2 |
DOIs | |
State | Published - 2010 |
Event | 12th Annual Genetic and Evolutionary Computation Conference, GECCO-2010 - Portland, OR, United States Duration: Jul 7 2010 → Jul 11 2010 |
Other
Other | 12th Annual Genetic and Evolutionary Computation Conference, GECCO-2010 |
---|---|
Country/Territory | United States |
City | Portland, OR |
Period | 7/7/10 → 7/11/10 |
All Science Journal Classification (ASJC) codes
- Computational Theory and Mathematics
- Theoretical Computer Science