Knowledge extraction from artificial neural networks models

Zvi Boger, Hugo Guterman

Research output: Contribution to journalConference articlepeer-review

201 Scopus citations

Abstract

The paper describes the development and application of several techniques for knowledge extraction from trained ANN models, such as the identification of redundant inputs and hidden neurons, deriving of causal relationships between inputs and outputs, and analysis of the hidden neuron behavior in classification ANN. Example of the application of these techniques is given of the faulty LED display benchmark. References of the application of these techniques are given of diverse large scale ANN models of industrial processes.

Original languageEnglish
Pages (from-to)3030-3035
Number of pages6
JournalProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Volume4
StatePublished - 1 Dec 1997
Externally publishedYes
EventProceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 3 (of 5) - Orlando, FL, USA
Duration: 12 Oct 199715 Oct 1997

Fingerprint

Dive into the research topics of 'Knowledge extraction from artificial neural networks models'. Together they form a unique fingerprint.

Cite this