Heuristics for the extraction of rules from discrete-time recurrent neural networks
- 2 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 33-38
- https://doi.org/10.1109/ijcnn.1992.287212
Abstract
It is pointed out that discrete recurrent neural networks can learn to classify long strings of a regular language correctly when trained on a small finite set of positive and negative example strings. Rules defining the learned grammar can be extracted from networks by applying clustering heuristics in the output space of recurrent state neurons. Empirical evidence that there exists a correlation between the generalization performance of recurrent neural networks for regular language recognition and the rules that can be extracted from a neural network is presented. A heuristic that makes it possible to extract good rules from trained networks is given, and the method is tested on networks that are trained to recognize a simple regular language.< >Keywords
This publication has 8 references indexed in Scilit:
- Learning and Extracting Finite State Automata with Second-Order Recurrent Neural NetworksNeural Computation, 1992
- The Induction of Dynamical RecognizersMachine Learning, 1991
- Finding structure in timeCognitive Science, 1990
- Finite State Automata and Simple Recurrent NetworksNeural Computation, 1989
- A Learning Algorithm for Continually Running Fully Recurrent Neural NetworksNeural Computation, 1989
- Machine Learning Using a Higher Order Correlation NetworkPhysica D: Nonlinear Phenomena, 1986
- Inductive Inference: Theory and MethodsACM Computing Surveys, 1983
- Complexity of automaton identification from given dataInformation and Control, 1978