Tools and Techniques for Decision Tree Learning

Decision tree learning is an important field of machine learning. In this study we examine both formal and practical aspects of decision tree learning. We aim at answering to two important needs: The need for better motivated decision tree learners and an environment facilitating experimentation with inductive learning algorithms. As results we obtain new practical tools and useful techniques for decision tree learning. First, we derive the practical decision tree learner Rank based on the Findmin protocol of Ehrenfeucht and Haussler. The motivation for the changes introduced to the method comes from empirical experience, but we prove the correctness of the modifications in the probably approximately correct learning framework. The algorithm is enhanced by extending it to operate in the multiclass situations, making it capable of working within the incremental setting, and providing noise tolerance into it. Together these modifications entail practicability through a formal development..