Integrating Bayesian Networks into Knowledge-Intensive CBR
Agnar Aamodt, Helge Langseth · 1998
In this paper we propose an approach to knowledge intensive CBR, where explanations are generated from a domain model consisting partly of a semantic network and partly of a Bayesian network (BN). The BN enables learning within this domain model based on the observed data. The domain model is used to focus the retrieval and reuse of past cases, as well as the indexing when learning a new case. Essentially, the BN-powered submodel works in parallel with the semantic network model to generate a statistically sound contribution to case indexing, retrieval and explanation. 1. Introduction and background In knowledge-intensive CBR a model of general domain knowledge is utilized to support the processes of retrieval and reuse of past cases, as well as to learn new cases. The role of the general domain knowledge is to explain why two cases are similar based on semantic and pragmatic criteria, how a past solution may be adapted to a new problem case, and/or what to retain from a case just sol...