@inproceedings{9913c633c1554fca8633a055e6e0ff4e,
title = "Heuristics for the Extraction of Rules from Discrete-Time Recurrent Neural Networks",
abstract = "Discrete recurrent neural networks can learn to correctly classify long strings of a regular language when trained on a small finite set of positive and negative example strings [Giles 90]. Rules defining the learned grammar can be extracted from networks by applying clustering heuristics in the output space of recurrent state neurons. We give 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. We present a heuristic that permits us to extract good rules from trained networks and test our method on networks which are trained to recognize a simple regular language.",
author = "Omlin, {C. W.} and Giles, {C. L.} and Miller, {C. B.}",
note = "Publisher Copyright: {\textcopyright} 1992 IEEE.; 1992 International Joint Conference on Neural Networks, IJCNN 1992 ; Conference date: 07-06-1992 Through 11-06-1992",
year = "1992",
doi = "10.1109/IJCNN.1992.287212",
language = "English (US)",
series = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "33--38",
booktitle = "Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992",
address = "United States",
}