Revising Engineering Models: Combining Computational Discovery with Knowledge
Abstract
Developing mathematical models that represent physical devices is a difficult and time consuming task. In this paper, we present a hybrid approach to modeling that combines machine learning methods with knowledge from a human domain expert. Specifically, we propose a system for automatically revising an initial model provided by an expert with an equation discovery program that is tightly constrained by domain knowledge. We apply our system to learning an improved model of a battery on the International Space Station from telemetry data. Our results suggest that this hybrid approach can reduce model development time and improve model quality.
Cite
Text
Bay et al. "Revising Engineering Models: Combining Computational Discovery with Knowledge." European Conference on Machine Learning, 2002. doi:10.1007/3-540-36755-1_2Markdown
[Bay et al. "Revising Engineering Models: Combining Computational Discovery with Knowledge." European Conference on Machine Learning, 2002.](https://mlanthology.org/ecmlpkdd/2002/bay2002ecml-revising/) doi:10.1007/3-540-36755-1_2BibTeX
@inproceedings{bay2002ecml-revising,
title = {{Revising Engineering Models: Combining Computational Discovery with Knowledge}},
author = {Bay, Stephen D. and Shapiro, Daniel G. and Langley, Pat},
booktitle = {European Conference on Machine Learning},
year = {2002},
pages = {10-22},
doi = {10.1007/3-540-36755-1_2},
url = {https://mlanthology.org/ecmlpkdd/2002/bay2002ecml-revising/}
}