Logistic model tree extraction from artificial neural networks

2.50
Hdl Handle:
http://hdl.handle.net/2173/31052
Title:
Logistic model tree extraction from artificial neural networks
Authors:
Dancey, Darren; Bandar, Zuhair A.; McLean, David A.
Citation:
IEEE transactions on systems, man and cybernetics part B (Cybernetics), 2007, vol. 37, no. 4, pp. 794-802
Publisher:
IEEE
Issue Date:
Aug-2007
URI:
http://hdl.handle.net/2173/31052
DOI:
10.1109/TSMCB.2007.895334
Additional Links:
http://ieeexplore.ieee.org/servlet/opac?punumber=3477
Abstract:
Artificial neural networks (ANNs) are a powerful and widely used pattern recognition technique. However, they remain “black boxes” giving no explanation for the decisions they make. This paper presents a new algorithm for extracting a logistic model tree (LMT) from a neural network, which gives a symbolic representation of the knowledge hidden within the ANN. Landwehr’s LMTs are based on standard decision trees, but the terminal nodes are replaced with logistic regression functions. This paper reports the results of an empirical evaluation that compares the new decision tree extraction algorithm with Quinlan’s C4.5 and ExTree. The evaluation used 12 standard benchmark datasets from the University of California, Irvine machine-learning repository. The results of this evaluation demonstrate that the new algorithm produces decision trees that have higher accuracy and higher fidelity than decision trees created by both C4.5 and ExTree.
Type:
Article
Language:
en
Description:
This article was originally published following peer-review in IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics, published by and copyright IEEE.
Keywords:
Artificial intelligence; Feedforward neural networks; Multilayer perceptrons (MPLs); Neural networks
ISSN:
1083-4419
EISSN:
1941-0492

Full metadata record

DC FieldValue Language
dc.contributor.authorDancey, Darren-
dc.contributor.authorBandar, Zuhair A.-
dc.contributor.authorMcLean, David A.-
dc.date.accessioned2008-07-07T08:16:53Z-
dc.date.available2008-07-07T08:16:53Z-
dc.date.issued2007-08-
dc.identifier.citationIEEE transactions on systems, man and cybernetics part B (Cybernetics), 2007, vol. 37, no. 4, pp. 794-802en
dc.identifier.issn1083-4419-
dc.identifier.doi10.1109/TSMCB.2007.895334-
dc.identifier.urihttp://hdl.handle.net/2173/31052-
dc.descriptionThis article was originally published following peer-review in IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics, published by and copyright IEEE.en
dc.description.abstractArtificial neural networks (ANNs) are a powerful and widely used pattern recognition technique. However, they remain “black boxes” giving no explanation for the decisions they make. This paper presents a new algorithm for extracting a logistic model tree (LMT) from a neural network, which gives a symbolic representation of the knowledge hidden within the ANN. Landwehr’s LMTs are based on standard decision trees, but the terminal nodes are replaced with logistic regression functions. This paper reports the results of an empirical evaluation that compares the new decision tree extraction algorithm with Quinlan’s C4.5 and ExTree. The evaluation used 12 standard benchmark datasets from the University of California, Irvine machine-learning repository. The results of this evaluation demonstrate that the new algorithm produces decision trees that have higher accuracy and higher fidelity than decision trees created by both C4.5 and ExTree.en
dc.language.isoenen
dc.publisherIEEEen
dc.relation.urlhttp://ieeexplore.ieee.org/servlet/opac?punumber=3477en
dc.subjectArtificial intelligenceen
dc.subjectFeedforward neural networksen
dc.subjectMultilayer perceptrons (MPLs)en
dc.subjectNeural networksen
dc.titleLogistic model tree extraction from artificial neural networksen
dc.typeArticleen
dc.identifier.eissn1941-0492-
All Items in e-space are protected by copyright, with all rights reserved, unless otherwise indicated.