Learning taxonomic relation by case-based reasoning Author: Ken Satoh Source: Theoretical Computer Science Vol. 348, Issue 1, December 2005, pp. 58-69 (Special Issue Algorithmic Learning Theory (ALT 2000)). Abstract. In this paper, we propose a learning method of minimal casebase to represent taxonomic relation in a tree-structured concept hierarchy. We firstly propose case-based taxonomic reasoning and show an upper bound of necessary positive cases and negative cases to represent a relation. Then, we give a learning method of a minimal casebase with sampling and membership queries. We analyze this learning method by sample complexity and query complexity in the framework of PAC learning. Keywords: Case-based reasoning; Taxonomy; PAC learning

©Copyright 2005 Elsevier Science B.V.