On Concept Space and Hypothesis Space in Case-Based Learning Algorithms

Abstract

In order to learn more about the behaviour of case-based reasoners as learning systems, we formalise a simple case-based learner as a PAC learning algorithm. We show that the case-based representation 〈 CB, σ 〉 is rich enough to express any boolean function. We define a family of simple case-based learning algorithms which use a single, fixed similarity measure and we give necessary and sufficient conditions for the consistency of these learning algorithms in terms of the chosen similarity measure. Finally, we consider the way in which these simple algorithms, when trained on target concepts from a restricted concept space, often output hypotheses which are outside the chosen concept space. A case study investigates this relationship between concept space and hypothesis space and concludes that the case-based algorithm studied is a less than optimal learning algorithm for the chosen, small, concept space.