Extracting decision trees from trained neural networks

Authors:
Olcay Boz
Affiliations:
AT&T Labs, Middletown, NJ
Venue:
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
Year:
2002

Citing 5
Cited 4

Symbolic and Neural Learning Algorithms: An Experimental Comparison

Machine Learning
Performance comparisons between backpropagation networks and classification trees on three real-world applications

Advances in neural information processing systems 2
A Further Comparison of Splitting Rules for Decision-Tree Induction

Machine Learning
Extracting comprehensible models from trained neural networks

Extracting comprehensible models from trained neural networks
Converting a trained neural network to a decision tree dectext - decision tree extractor

Converting a trained neural network to a decision tree dectext - decision tree extractor

Simple mimetic classifiers

MLDM'03 Proceedings of the 3rd international conference on Machine learning and data mining in pattern recognition
Admission control for a responsive distributed middleware using decision trees to model run-time parameters

Parallel Computing
A novel classification model for cotton yarn quality based on trained neural network using genetic algorithm

Knowledge-Based Systems
Comprehensible classification models: a position paper

ACM SIGKDD Explorations Newsletter

Quantified Score

Hi-index	0.00

Visualization

Abstract

Neural Networks are successful in acquiring hidden knowledge in datasets. Their biggest weakness is that the knowledge they acquire is represented in a form not understandable to humans. Researchers tried to address this problem by extracting rules from trained Neural Networks. Most of the proposed rule extraction methods required specialized type of Neural Networks; some required binary inputs and some were computationally expensive. Craven proposed extracting MofN type Decision Trees from Neural Networks. We believe MofN type Decision Trees are only good for MofN type problems and trees created for regular high dimensional real world problems may be very complex. In this paper, we introduced a new method for extracting regular C4.5 like Decision Trees from trained Neural Networks. We showed that the new method (DecText) is effective in extracting high fidelity trees from trained networks. We also introduced a new discretization technique to make DecText be able to handle continuous features and a new pruning technique for finding simplest tree with the highest fidelity.