Refining Domain Theories Expressed as Finite-State Automata
Abstract
The kBANN system uses neural networks to refine domain theories. Currently, domain knowledge in kBANN is expressed as non-recursive, propositional rules. We extend kBANN to domain theories expressed as finite-state automata. We apply finite-state KBANN to the task of predicting how proteins fold, producing a small but statistically significant gain in accuracy over both a standard neural network approach and a non-learning algorithm from the biological literature. Our method shows promise at solving this and other real-world problems that can be described in terms of state-dependent decisions.
Cite
Text
Maclin and Shavlik. "Refining Domain Theories Expressed as Finite-State Automata." International Conference on Machine Learning, 1991. doi:10.1016/B978-1-55860-200-7.50107-0Markdown
[Maclin and Shavlik. "Refining Domain Theories Expressed as Finite-State Automata." International Conference on Machine Learning, 1991.](https://mlanthology.org/icml/1991/maclin1991icml-refining/) doi:10.1016/B978-1-55860-200-7.50107-0BibTeX
@inproceedings{maclin1991icml-refining,
title = {{Refining Domain Theories Expressed as Finite-State Automata}},
author = {Maclin, Richard and Shavlik, Jude W.},
booktitle = {International Conference on Machine Learning},
year = {1991},
pages = {524-528},
doi = {10.1016/B978-1-55860-200-7.50107-0},
url = {https://mlanthology.org/icml/1991/maclin1991icml-refining/}
}