Acquiring schemata through understanding and generalizing plans
GERALD F. DEJONG · International Joint Conference on Artificial Intelligence · 1983
This paper discusses explanatory schema acquisition, a learning technique with several interesting properties. It does not require a teacher or concept matching predicate to be provided. It does not reply on searching a concept space to produce generalizations. It can acquire a new concept based on only one input example, although later inputs might result in refinement of learned concepts. These features are made possible by taking a very knowledge-based approach.