HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Vahed, A. Articles by Omlin, C.W. Search for Related Content PubMed PubMed Citation Articles by Vahed, A. Articles by Omlin, C.W.

A Machine Learning Method for Extracting Symbolic Knowledge from Recurrent Neural Networks

avahed{at}uwc.ac.za, Department of Computer Science, University of the Western Cape, 7535 Bellville, South Africa

C.W. Omlin

comlin{at}uwc.ac.za, Department of Computer Science, University of the Western Cape, 7535 Bellville, South Africa

Neural networks do not readily provide an explanation of the knowledge stored in their weights as part of their information processing. Until recently, neural networks were considered to be black boxes, with the knowledge stored in their weights not readily accessible. Since then, research has resulted in a number of algorithms for extracting knowledge in symbolic form from trained neural networks. This article addresses the extraction of knowledge in symbolic form from recurrent neural networks trained to behave like deterministic finite-state automata (DFAs). To date, methods used to extract knowledge from such networks have relied on the hypothesis that networks' states tend to cluster and that clusters of network states correspond to DFA states. The computational complexity of such a cluster analysis has led to heuristics that either limit the number of clusters that may form during training or limit the exploration of the space of hidden recurrent state neurons. These limitations, while necessary, may lead to decreased fidelity, in which the extracted knowledge may not model the true behavior of a trained network, perhaps not even for the training set. The method proposed here uses a polynomial time, symbolic learning algorithm to infer DFAs solely from the observation of a trained network's input-output behavior. Thus, this method has the potential to increase the fidelity of the extracted knowledge.

This article has been cited by other articles:

				H. Jacobsson The Crystallizing Substochastic Sequential Machine Extractor: CrySSMEx. Neural Comput., September 1, 2006; 18(9): 2211 - 2255. [Abstract] [Full Text] [PDF]

				H. Jacobsson Rule Extraction from Recurrent Neural Networks: A Taxonomy and Review Neural Comput., June 1, 2005; 17(6): 1223 - 1263. [Abstract] [Full Text] [PDF]