Inversion of a neural network via interval arithmetic for rule extraction

Authors:
Carlos Hernández-Espinosa;Mercedes Fernández-Redondo;Mamen Ortiz-Gómez
Affiliations:
Universidad Jaume I, Castellón, Spain;Universidad Jaume I, Castellón, Spain;Universidad Jaume I, Castellón, Spain
Venue:
ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
Year:
2003

Citing 4
Cited 0

Handbook of Neural Computing Applications

Handbook of Neural Computing Applications
Effective Data Mining Using Neural Networks

IEEE Transactions on Knowledge and Data Engineering
Symbolic Interpretation of Artificial Neural Networks

IEEE Transactions on Knowledge and Data Engineering
Generalized Analytic Rule Extraction for Feedforward Neural Networks

IEEE Transactions on Knowledge and Data Engineering

Quantified Score

Hi-index	0.02

Visualization

Abstract

In this paper we propose a new algorithm for rule extraction from a trained Multilayer Feedforward network. The algorithm is based on an interval arithmetic network inversion for particular target outputs. The types of rules extracted are N-dimensional intervals in the input space. We have performed experiments with four databases and the results are very interesting. One rule extracted by the algorithm can cover 86% of the neural network output and in other cases 64 rules cover 100% of the neural network output.