Symbolic rule extraction from neural networks: an application to identifying organizations adopting IT

摘要: Interest in the application of neural networks as tools for decision support has been growing recent years. A major drawback often associated with is difficulty understanding knowledge represented by a trained network. This paper describes an approach that can extract symbolic rules from networks. We illustrate how successfully extracted data set collected survey service sectors United Kingdom. The were then used to distinguish between organizations using computers those do not. classification scheme based on these was identify specific segments market promoting adoption information technology. are not only concise but also outperform discriminant analysis terms predictive accuracy.