Learning Physics via Explanation-Based Learning of Correctness and Analogical Search Control
Abstract
Cascade models humans learning college physics by studying examples and solving problems. It simulates the main qualitative phenomena visible in human protocols of learning, including several strategies for analogical and non-analogical problem solving, and two strategies for studying examples. It learns at the knowledge level by acquiring new physics rules, and it learns search control knowledge. Most importantly, it models a recently observed phenomenon, the self-explanation effect, which correlates students' example studying strategies with the amount they learn.
Cite
Text
VanLehn and Jones. "Learning Physics via Explanation-Based Learning of Correctness and Analogical Search Control." International Conference on Machine Learning, 1991. doi:10.1016/B978-1-55860-200-7.50026-XMarkdown
[VanLehn and Jones. "Learning Physics via Explanation-Based Learning of Correctness and Analogical Search Control." International Conference on Machine Learning, 1991.](https://mlanthology.org/icml/1991/vanlehn1991icml-learning/) doi:10.1016/B978-1-55860-200-7.50026-XBibTeX
@inproceedings{vanlehn1991icml-learning,
title = {{Learning Physics via Explanation-Based Learning of Correctness and Analogical Search Control}},
author = {VanLehn, Kurt and Jones, Randolph M.},
booktitle = {International Conference on Machine Learning},
year = {1991},
pages = {110-114},
doi = {10.1016/B978-1-55860-200-7.50026-X},
url = {https://mlanthology.org/icml/1991/vanlehn1991icml-learning/}
}