ML Anthology

Towards a Formal Analysis of EBL

Russell Greiner
ICML 1989 pp. 450-453
doi:10.1016/b978-1-55860-036-2.50114-4 /icml/1989/greiner1989icml-formal/

Abstract

“Explanation-based learning” – i.e., incorporating new redundant rules suggested by earlier problem solving experiences – is an attempt to speed up problem solving. Recent empirical evidence, however, has shown that the resulting systems are not always more efficient on subsequent problems. This paper provides a formal framework for analyzing whether these new rules should be added, and if so, where they should appear in the overall derivation strategy. It also discusses some of the complexities inherent in this task.

ICML Semantic Scholar

Cite

Text

Greiner. "Towards a Formal Analysis of EBL." International Conference on Machine Learning, 1989. doi:10.1016/b978-1-55860-036-2.50114-4

Markdown

[Greiner. "Towards a Formal Analysis of EBL." International Conference on Machine Learning, 1989.](https://mlanthology.org/icml/1989/greiner1989icml-formal/) doi:10.1016/b978-1-55860-036-2.50114-4

BibTeX

@inproceedings{greiner1989icml-formal,
  title     = {{Towards a Formal Analysis of EBL}},
  author    = {Greiner, Russell},
  booktitle = {International Conference on Machine Learning},
  year      = {1989},
  pages     = {450-453},
  doi       = {10.1016/b978-1-55860-036-2.50114-4},
  url       = {https://mlanthology.org/icml/1989/greiner1989icml-formal/}
}