Abstract
This article describes a connectionist method for refining algorithms represented as generalized finite-state automata. The method translates the rule-like knowledge in an automaton into a corresponding artificial neural network, and then refines the reformulated automaton by applying backpropagation to a set of examples. This technique for translating an automaton into a network extends the KBANN algorithm, a system that translates a set of prepositional 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, FSKBANN is used to improve the Chou–Fasman algorithm, a method for predicting how globular proteins fold. Empirical evidence shows that the multistrategy approach of FSKBANN leads to a statistically-significantly, more accurate solution than both the original Chou–Fasman algorithm and a neural network trained using the standard approach. Extensive statistics report the types of errors made by the Chou–Fasman algorithm, the standard neural network, and the FSKBANN network.
Original language | English (US) |
---|---|
Pages (from-to) | 195-215 |
Number of pages | 21 |
Journal | Machine Learning |
Volume | 11 |
Issue number | 2 |
DOIs | |
State | Published - May 1993 |
Keywords
- Chou–Fasman algorithm
- Multistrategy learning
- finite-state automata
- neural networks
- protein folding
- theory refinement