Library Header Image
LSE Research Online LSE Library Services

A probabilistic approach to case-based inference

Anthony, Martin and Ratsaby, Joel (2015) A probabilistic approach to case-based inference. Theoretical Computer Science, 589. pp. 61-75. ISSN 0304-3975

PDF - Accepted Version
Download (547kB) | Preview

Identification Number: 10.1016/j.tcs.2015.04.016


The central problem in case based reasoning (CBR) is to infer a solution for a new problem-instance by using a collection of existing problem-solution cases. The basic heuristic guiding CBR is the hypothesis that similar problems have similar solutions. Recently, some attempts at formalizing CBR in a theoretical framework have been made, including work by Hullermeier who established a link between CBR and the probably approximately correct (PAC) theoretical model of learning in his 'case-based inference' (CBI) formulation. In this paper we develop further such probabilistic modelling, framing CBI it as a multi-category classification problem. We use a recently-developed notion of geometric margin of classification to obtain generalization error bounds.

Item Type: Article
Official URL:
Additional Information: © 2015 Elsevier
Divisions: Mathematics
Subjects: Q Science > QA Mathematics
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Date Deposited: 23 Apr 2015 10:58
Last Modified: 16 May 2024 02:01

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics