Knowledge extraction using artificial neural networks: application to radar target identification

Authors:
J.-F. Remm;F. Alexandre
Affiliations:
LORIA-INRIA, BP 239, F-54506 Vandæuvre, France;LORIA-INRIA, BP 239, F-54506 Vandæuvre, France
Venue:
Signal Processing
Year:
2002

Citing 3
Cited 4

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Optimal brain damage

Advances in neural information processing systems 2
Backpropagation: theory, architectures, and applications

Backpropagation: theory, architectures, and applications

Greedy rule generation from discrete data and its use in neural network rule extraction

Neural Networks
Deinterleaving pulse trains in unconventional circumstances using multiple hypothesis tracking algorithm

Signal Processing
Extracting reduced logic programs from artificial neural networks

Applied Intelligence
Current trends on knowledge extraction and neural networks

ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II

Quantified Score

Hi-index	0.08

Visualization

Abstract

Artificial neural networks are efficient for performing signal processing but are not able to explain their decision nor to extract knowledge from data. We propose here a way to extract rules and hints from the hidden layers of a multilayered perceptron. The network is first pruned and then the progressive use of a simpler transfer function can allow such knowledge extraction. This method has been successfully applied to radar signal identification.