Untitled

Abstract

Abstract. This article describes how a reasoner can improve its understanding of an incompletely understood domain through the application of what it already knows to novel problems in that domain. Case-based reasoning is the process of using past experiences stored in the reasoner's memory to understand novel situations or solve novel problems. However, this process assumes that past experiences are well understood and provide good "lessons" to be used for future situations. This assumption is usually false when one is learning about a novel domain, since situations encountered previously in this domain might not have been understood completely. Furthermore, the reasoner may not even have a case that adequately deals with the new situation, or may not be able to access the case using existing indices. We present a theory of incremental learning based on the revision of previously existing case knowledge in response to experiences in such situations. The theory has been implemented in a case-based story understanding program that can (a) learn a new case in situations where no case already exists, (b) learn how to index the case in memory, and (c) incrementally refine its understanding of the case by using it to reason about new situations, thus evolving a better understanding of its domain through experience. This research complements work in case-based reasoning by providing mechanisms by which a case library can be automatically built for use by a case-based reasoning program.Keywords: Case-based learning, explanation-based learning, index learning, questions, incremental learning Case-based learningCase-based reasoning programs deal with the issue of using past experiences or cases to understand, plan for, or learn from novel situations (e.g., see Kolodner, 1988;Hammond, 1989). This happens according to the following process: (a) Use the problem description (problems, anomalies, goals) to get reminded of the old case; (b) Retrieve the results (lessons, explanations, plans) of processing the old case and give them to the problem-solver, understander, or planner; (c) Adapt the results from the old case to the specifics of the new situation; and (d) Apply the adapted results to the new situation. In some case-based reasoning programs, there is a further step (e) in which the old and new solutions are generalized to increase the applicability of the solutions.The intent behind case-based reasoning is to avoid the effort involved in re-deriving these lessons, explanations, or plans by simply reusing the results from previous cases. However, this process relies on three assumptions: (1) A case is available for the situation at hand; (2) The case is correctly indexed in memory so that it can be retrieved for use in the current situation using the cues that the situation provides; and (3) The case is well understood and provides good "lessons" to be used in this and future situations.In other words, case-based reasoning programs rely on the existence of a case library that can provide the right cases when they are n...