Dancey, Darren and McLean, David A. and Bandar, Zuhair A. (2004) Decision tree extraction from trained neural networks. In: UNSPECIFIED.
Download (87kB) | Preview
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.
|Item Type:||Conference or Workshop Item (Paper)|
|Additional Information:||This paper was originally presented at the 17th International FLAIRS Conference, Florida, United States, 17-19 May 2004.|
|Divisions:||Faculties > Faculty of Science and Engineering > Department of Computing, Mathematics & Digital Technology
Faculties > Faculty of Science and Engineering > Department of Computing and Mathematics: Intelligent Systems Group
Legacy Research Institutes > Dalton Research Institute > Computer Science
|Date Deposited:||09 Jul 2008 09:03|
|Last Modified:||15 Sep 2016 13:45|
Actions (login required)