Abstract
We describe a method for using machine learning to refine algorithms represented as generalized finite-state automata. The knowledge in an automaton is translated into an artificial neural network, and then refined with backpropagation on a set of examples. Our technique for translating an automaton into a network extends KBANN, a system that translates a set of propositional rules into a corresponding neural network. The extended system, FSKBANN, allows one to refine the large class of algorithms that can be represented as state-based processes. As a test, we use FSKBANN to refine the Chou-Fasman algorithm, a method for predicting how globular proteins fold. Empirical evidence shows the refined algorithm FSKBANN produces is statistically significantly more accurate than both the original Chou-Fasman algorithm and a neural network trained using the standard approach.
Original language | English (US) |
---|---|
Title of host publication | Proceedings Tenth National Conference on Artificial Intelligence |
Publisher | Publ by AAAI |
Pages | 165-170 |
Number of pages | 6 |
ISBN (Print) | 0262510634 |
State | Published - Dec 1 1992 |
Event | Proceedings Tenth National Conference on Artificial Intelligence - AAAI-92 - San Jose, CA, USA Duration: Jul 12 1992 → Jul 16 1992 |
Other
Other | Proceedings Tenth National Conference on Artificial Intelligence - AAAI-92 |
---|---|
City | San Jose, CA, USA |
Period | 7/12/92 → 7/16/92 |