Explanation-based learning

Explanation-based learning (EBL) is a form of machine learning that exploits a very strong, or even perfect, domain theory to make generalizations or form concepts from training examples.[1]
EBL software takes four inputs: ...

Explanation-Based Learning
An Explanation-based Learning (EBL ) system accepts an example (i.e. a training example) and explains what it learns from the example. The EBL system takes only the relevant aspects of the training.

explanation-based learning a kind of machine learning in which the result of learning from a new example is a general rule that explains the basis for the classification of the example.

Explanation-based learning, speedup learning; utility problem, analogy, resurgence of connectionism (PDP, ANN), PAC learning, experimental evaluation.
In 1980, First workshop on Machine Learning was at CMU attended by 30 participants.

3 Explanation-Based Learning . . . . . . . . . . . . . . . . . . . . . . . . 780
19.4 Learning Using Relevance Information . . . . . . . . . . . . . . . . . . . 784
19.5 Inductive Logic Programming . . . . . . . . . . . . . . . . . . . . . . . . 788 ...

See also: Artificial intelligence, Knowledge, AI, Neural network, Natural language processing