Refining Domain Theories Expressed as Finite-State Automata [chapter]

Richard Maclin, Jude W. Shavlik
1991 Machine Learning Proceedings 1991  
The KBANN system uses neural networks to refine domain theories. Currently, domain knowledge in KBANN is expressed as nonrecursive, 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
more » ... ing this and other real-world problems that can be described in terms of statedependent decisions.
doi:10.1016/b978-1-55860-200-7.50107-0 dblp:conf/icml/MaclinS91 fatcat:u6vjzvxys5h2jfj4dxahmqfkdi