2.50
Hdl Handle:
http://hdl.handle.net/2173/31354
Title:
Decision tree extraction from trained neural networks
Authors:
Dancey, Darren; McLean, David A.; Bandar, Zuhair A.
Publisher:
American Association for Artificial Intelligence
Issue Date:
May-2004
URI:
http://hdl.handle.net/2173/31354
Additional Links:
http://uhaweb.hartford.edu/flairs04/; http://www.aaai.org/
Abstract:
Artificial Neural Networks (ANNs) have proved both a popular and powerful technique for pattern recognition tasks in a number of problem domains. However, the adoption of ANNs in many areas has been impeded, due to their inability to explain how they came to their conclusion, or show in a readily comprehendible form the knowledge they have obtained. This paper presents an algorithm that addresses these problems. The algorithm achieves this by extracting a Decision Tree, a graphical and easily understood symbolic representation of a decision process, from a trained ANN. The algorithm does not make assumptions about the ANN’s architecture or training algorithm; therefore, it can be applied to any type of ANN. The algorithm is empirically compared with Quinlan’s C4.5 (a common Decision Tree induction algorithm) using standard benchmark datasets. For most of the datasets used in the evaluation, the new algorithm is shown to extract Decision Trees that have a higher predictive accuracy than those induced using C4.5 directly.
Type:
Presentation
Language:
en
Description:
This paper was originally presented at the 17th International FLAIRS Conference, Florida, United States, 17-19 May 2004.

Full metadata record

DC FieldValue Language
dc.contributor.authorDancey, Darren-
dc.contributor.authorMcLean, David A.-
dc.contributor.authorBandar, Zuhair A.-
dc.date.accessioned2008-07-09T09:03:33Z-
dc.date.available2008-07-09T09:03:33Z-
dc.date.issued2004-05-
dc.identifier.urihttp://hdl.handle.net/2173/31354-
dc.descriptionThis paper was originally presented at the 17th International FLAIRS Conference, Florida, United States, 17-19 May 2004.en
dc.description.abstractArtificial Neural Networks (ANNs) have proved both a popular and powerful technique for pattern recognition tasks in a number of problem domains. However, the adoption of ANNs in many areas has been impeded, due to their inability to explain how they came to their conclusion, or show in a readily comprehendible form the knowledge they have obtained. This paper presents an algorithm that addresses these problems. The algorithm achieves this by extracting a Decision Tree, a graphical and easily understood symbolic representation of a decision process, from a trained ANN. The algorithm does not make assumptions about the ANN’s architecture or training algorithm; therefore, it can be applied to any type of ANN. The algorithm is empirically compared with Quinlan’s C4.5 (a common Decision Tree induction algorithm) using standard benchmark datasets. For most of the datasets used in the evaluation, the new algorithm is shown to extract Decision Trees that have a higher predictive accuracy than those induced using C4.5 directly.en
dc.language.isoenen
dc.publisherAmerican Association for Artificial Intelligenceen
dc.relation.urlhttp://uhaweb.hartford.edu/flairs04/en
dc.relation.urlhttp://www.aaai.org/en
dc.titleDecision tree extraction from trained neural networksen
dc.typePresentationen
All Items in e-space are protected by copyright, with all rights reserved, unless otherwise indicated.