Clustering and instance based learning in first order logic

Article type: Other

Authors: Ramon, Jan

Affiliations: K.U.Leuven, Department of Computer Science, Celestijnenlaan 200A, 3001 Heverlee, Belgium E‐mail: jan.ramon@cs.kuleuven.ac.be

Abstract: Instance based learning and clustering are popular methods in propositional machine learning. Both methods use a notion of similarity between objects. This dissertation investigates these methods in a relational setting. First, a number of new metrics are proposed. Next, these metrics are used to upgrade clustering and instance based learning to first order logic.

Keywords: Machine learning, inductive logic programming, instance based learning, clustering

Journal: AI Communications, vol. 15, no. 4, pp. 217-218, 2002