ABSTRACT
Case-based reasoning (CBR), inspired by people, was developed as a model for creating intelligent systems — systems that can reason by reference to previous experiences. Such systems, it was said, had the potential to behave more like real experts than did traditional expert systems. Reasoning based on experience would allow intelligent systems more flexibility and less brittleness than rulebased systems, and, with learning' from experience built into the architectures, the systems would become more capable over time (Kolodner & Simpson, 1989). Many experimental automated case-based reasoners have been created (see the lists, e.g., in Kolodner, 1993) and, indeed, CBR has proven to be quite a useful technology. More interesting to us, however, are the implications CBR holds as a model of cognition — implications about what it means to be a learner and implications about learning and education.
