Learning Case Adaptation :: Technology Case-Based Reasoning Essays

Learning Case Adaptation Computer models of case-based reasoning (CBR) generally guide case adaptation using a fixed set of adaptation rules. A difficult practical problem is how to identify the knowledge required to guide adaptation for particular tasks. Likewise, an open issue for CBR as a cognitive model is how case adaptation knowledge is learned. We describe a new approach to acquiring case adaptation knowledge. In this approach, adaptation problems are initially solved by reasoning from scratch, using abstract rules about structural transformations and general memory search heuristics. Traces of the processing used for successful rule-based adaptation are stored as cases to enable future adaptation to be done by case-based reasoning. When similar adaptation problems are encountered in the future, these adaptation cases provide task- and domain-specific guidance for the case adaptation process. We present the tenets of the approach concerning the relationship between memory search and case adaptation, t he memory search process, and the storage and reuse of cases representing adaptation episodes. These points are discussed in the context of ongoing research on DIAL, a computer model that learns case adaptation knowledge for case-based disaster response planning. 1 Introduction The fundamental principle of case-based reasoning (CBR) for problem-solving is that new problems are addressed by retrieving stored records of prior problem-solving episodes and adapting their solutions to fit new situations. In most case-based reasoning systems, the case adaptation process is guided by fixed case adaptation rules. Practical experience developing CBR systems has shown that it is difficult to establish appropriate case adaptation rules (e.g., Allemang, 1993; Leake, 1994). In defining adaptation rules, a key problem is the classic operationality/generality tradeoff that was first observed in research on explanation-based learning (e.g., Segre, 1987): Specific rules are easy to apply and are reliable, but only apply to a narrow range of adaptation problems; abstract rules span a broad range of potential adaptations but are often hard and expensive to apply because they do not provide task- and domain-specific guidance. In those CBR systems that do perform case adaptatio n, specific rules are often used, requiring that the developer perform difficult analysis of the task and domain to determine which rules will be needed. In practice, the problems of defining adaptation rules are so acute that many CBR applications simply omit case adaptation (e.g., Barletta, 1994). This paper presents a new method by which a case-based reasoning system can learn adaptation knowledge from experience.