TitleUsages of Generalization in CBR
Publication TypeConference Paper
Year of Publication2007
AuthorsArmengol E
EditorWeber R.O., Richter M.M
Conference NameLecture Notes in Artificial Intelligence
PublisherSpringer-Verlag
Number4626
Pagination31-45
Abstract

The aim of this paper is to analyze how the generalizations built by a CBR method can be used as local approximations of a concept. From this point of view, these local approximations can take a role similar to the global approximations built by eager learning methods. Thus, we propose that local approximations can be interpreted either as: 1) a symbolic similitude among a set of cases, 2) a partial domain model, or 3) an explanation of the system classification. We illustrate these usages by solving the Predictive Toxicology task.