Catalogue of Artificial Intelligence Techniques
Keywords: Constraint Back Propagation, EBL, Explanation-Based Generalisation, learning
Author(s): Roberto Desimone
Explanation-Based Learning (EBL) techniques are knowledge-based and require a great deal of knowledge about the domain of the concept to be learned. Instead of providing several instances of a concept (as in Focussing), only a single example is required for a new concept to be learned. The idea is that a strong domain theory not only helps in describing or explaining the new concept, but also guides the generalisation process, such that a great deal can be learned from a single example. Various EBL techniques have been developed: constraint back propagation, explanation-based generalisation, Precondition Analysis; mostly in domains where there is a strong body of domain knowledge.
- Mitchell, T.M., Keller, R.M. and Kedar-Cabelli, S.T., Explanation-based generalisation: a unifying view Machine Learning 1 (1986) no.1, 47--80.
- Horn, B.K.P., Robot Vision, MIT Press, Cambridge, Mass., 1986 (16).