A Framework for Combining Symbolic and Neural Learning
JUDE W. SHAVLIK · 1992
This article describes an approach to combining symbolic and connectionist approaches to machine learning. A three-stage framework is presented and the research of several groups is reviewed with respect to this framework. The first stage involves the insertion of symbolic knowledge into neural networks, the second addresses the refinement of this prior knowledge in its neural representation, while the third concerns the extraction of the refined symbolic knowledge. Experimental results and open research issues are discussed. Keywords: knowledge-based neural networks theory refinement use of prior knowledge rule extraction from neural networks the KBANN algorithm the NofM algorithm A shorter version of this paper will appear in Machine Learning. A Framework for Combining Symbolic and Neural Learning Jude W. Shavlik Computer Sciences Department University of Wisconsin - Madison Introduction The last ten or so years have produced an explosion in the amount of research on machine lear...