Proceedings

Understanding Neural Networks via Rule Extraction

Rudy Setiono, Huan Liu

Download BibTeX Cite

Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence. Connectionist Models. Pages 480-486.

Abstract

Although backpropagation neural networks generally predict better than decision trees do for pattern classification problems, they are often regarded as bla~k boxes, i.e., their predictions are not as interpretable as those of decision trees. This paper argues that this is because there has been no proper technique that enables us to do so. With an algorithm that can extract rules 1 , by drawing parallels with those of decision trees, we show that the predictions of a network can be explained via rules extracted from it, thereby, the network can be understood. Experiments demonstrate that rules extracted from neural networks are comparable with those of decision trees in terms of predictive accuracy, number of rules and average number of conditions for a rule; they preserve high predictive accuracy of original networks.

Rudy Setiono, and Huan Liu. 1995. Understanding Neural Networks via Rule Extraction. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, IJCAI-95. IJCAI, 480–486. https://ijcai.org/proceedings/1995/63
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards