Improving rule extraction from neural networks by modifying hidden layer representations

Authors:
Thuan Q. Huynh;James A. Reggia
Affiliations:
Department of Computer Science, University of Maryland, College Park, Maryland;Department of Computer Science, University of Maryland, College Park, Maryland
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 11
Cited 0

C4.5: programs for machine learning

C4.5: programs for machine learning
Extracting Refined Rules from Knowledge-Based Neural Networks

Machine Learning
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
FERNN: An Algorithm for Fast Extraction of Rules fromNeural Networks

Applied Intelligence
Symbolic Interpretation of Artificial Neural Networks

IEEE Transactions on Knowledge and Data Engineering
A Probabilistic Classification System for Predicting the Cellular Localization Sites of Proteins

Proceedings of the Fourth International Conference on Intelligent Systems for Molecular Biology
NeuroRule: A Connectionist Approach to Data Mining

VLDB '95 Proceedings of the 21th International Conference on Very Large Data Bases
Chi2: Feature Selection and Discretization of Numeric Attributes

TAI '95 Proceedings of the Seventh International Conference on Tools with Artificial Intelligence
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Rule Extraction from Recurrent Neural Networks: A Taxonomy and Review

Neural Computation
The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a new method for extracting symbolic rules from multilayer feedforward neural networks. Our approach is to encourage backpropagation to learn a sparser representation at the hidden layer and to use the improved representation to extract fewer, easier to understand rules. A new error term defined over the hidden layer is added to the standard sum of squared error so that the total squared distance between hidden activation vectors is increased. We show that this method helps extract fewer rules without decreasing classification accuracy in four publicly available data sets.