http://hdl.handle.net/2173/31425 Tue, 18 Jun 2013 23:54:13 GMT 2013-06-18T23:54:13Z http://hdl.handle.net/2173/31354 Title: Decision tree extraction from trained neural networks Authors: Dancey, Darren; McLean, David A.; Bandar, Zuhair A. 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. Description: This paper was originally presented at the 17th International FLAIRS Conference, Florida, United States, 17-19 May 2004. Sat, 01 May 2004 00:00:00 GMT http://hdl.handle.net/2173/31354 2004-05-01T00:00:00Z http://hdl.handle.net/2173/31052 Title: Logistic model tree extraction from artificial neural networks Authors: Dancey, Darren; Bandar, Zuhair A.; McLean, David A. 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. 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. Wed, 01 Aug 2007 00:00:00 GMT http://hdl.handle.net/2173/31052 2007-08-01T00:00:00Z