Sciweavers

ESANN
2003

A new rule extraction algorithm based on interval arithmetic

14 years 1 months ago
A new rule extraction algorithm based on interval arithmetic
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 database 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.
Carlos Hernández-Espinosa, Mercedes Fern&aa
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2003
Where ESANN
Authors Carlos Hernández-Espinosa, Mercedes Fernández-Redondo, Mamen Ortiz-Gómez
Comments (0)