Why and How to Learn Why: Analysis-Based Generalization of Procedures.

Computer learners often develop explanations of events they observe during training. Recent work on generalization suggests that explanations may be valuable in permitting learners to develop generalizations from one or a few examples. We explore this idea by describing four generalization paradigms in which explanations play a part explanation-based generalization EBG, structure mapping analogical generalization SMAG, modificational analogical generalization MAG and synthetic generalization SG. We describe a model, the EXPL system, capable of applying MAG or SG to the generalization of simple procedures in human-computer interaction. We present evidence that EXPLs analysis procedure, which constructs explanations as needed by MAG or SG, embodies heuristic principles used by human learners, and that MAG provides a good account of some human generalization, when retention of examples is not a problem.