Meta-learning from an experiment database
Kurt Driessens, Gitte Vanwinckelen, Hendrik Blockeel · Lirias · 2012
In this short paper, we present a student project run as part of the Machine Learning and Inductive Inference course at KU Leuven during the 2010-2011 academic year. The goal of the project was to analyze a Machine Learning Experiment database, using standard SQL queries and data mining tools with the goals of (1) giving the students some practice with applying the machine learning techniques on a real problem, (2) teaching them something about the properties of machine learning algorithms and (3) training the students’ research skills by having them study literature on meta-learning to search for interesting background information and suggestions on how to approach the project and obtain meaningful results.