The truth is in there: directions and challenges in extracting rules from trained artificial neural networks

A recognized impediment to the more widespread utilisation of Artificial Neural Networks (ANNs) is the absence of a capability to explain, in a humancomprehensible form, either the process by which a trained ANN arrives at a specific decision/result or, in general, the totality of knowledge embedded therein. Recently there has been a proliferation of techniques aimed at redressing this situation by extracting the knowledge embedded in the trained ANN as a set of symbolic rules. This paper shows that the original schema for categorizing ANN rule extraction techniques proposed by Andrews, Diederich, and Tickle (1995) is able to accommodate these recent developments in the field. In addition attention is drawn to what are seen to be some of the key challenges in the area including the identification of factors which appear to limit what is actually achievable through the rule