Learning Procedural Knowledge in the EBG Context
Abstract
An extended explanation-based method of learning concept definitions is described. The extensions involve learning procedural knowledge from more than one example. The method is geared towards procedural descriptions of sequences of actions, where actions are represented by ordered sets of predicates. Additional constraints on occurrence of predicates within the ordered sets are learned by the method. The algorithm is illustrated with the example of the concept of taking a subway, learned from different training episodes in several cities around the world.
Cite
Text
Matwin and Morin. "Learning Procedural Knowledge in the EBG Context." International Conference on Machine Learning, 1989. doi:10.1016/B978-1-55860-036-2.50056-4Markdown
[Matwin and Morin. "Learning Procedural Knowledge in the EBG Context." International Conference on Machine Learning, 1989.](https://mlanthology.org/icml/1989/matwin1989icml-learning/) doi:10.1016/B978-1-55860-036-2.50056-4BibTeX
@inproceedings{matwin1989icml-learning,
title = {{Learning Procedural Knowledge in the EBG Context}},
author = {Matwin, Stan and Morin, Johanne},
booktitle = {International Conference on Machine Learning},
year = {1989},
pages = {197-199},
doi = {10.1016/B978-1-55860-036-2.50056-4},
url = {https://mlanthology.org/icml/1989/matwin1989icml-learning/}
}