Template-based procedures for neural network interpretation

Neural Networks

Volumn 12, Issue 3, 1999, Pages 479-498

  Alexander, J A ^a   Mozer, M C ^a  

^a UCB 450   (United States)

Author keywords

Boolean; Connectionist networks; Neural networks; Rule extraction; Sigmoidal units

Indexed keywords

BOOLEAN FUNCTIONS; CODES (SYMBOLS); COMPUTATIONAL COMPLEXITY; COMPUTER SIMULATION; MULTILAYER NEURAL NETWORKS; RECURSIVE FUNCTIONS;

CONNECTIONIST NETWORKS; RULE EXTRACTION; SIGMOIDAL UNITS;

FEEDFORWARD NEURAL NETWORKS;

ALGORITHM; HUMAN; INFORMATION PROCESSING; LEARNING; MATHEMATICAL ANALYSIS; MATHEMATICAL PARAMETERS; NERVE CELL NETWORK; PRIORITY JOURNAL; REVIEW;

EID: 0032931822     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(99)00009-X     Document Type: Article

References (26)

1. Bridle J.S. Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition. Fogelman-Soulie F., Herault J. Neuro-computing: algorithms, architectures and applications. 1989;227 Springer, Berlin.
2. Dinsmore, J. (Ed.) (1992). The symbolic and connectionist paradigms: closing the gap. Hillsdale, NJ: Erlbaum (Lawrence).
3. Dolan C.P., Smolensky P. Tensor product production system: a modular architecture and representation. Connection Science. 1:1989;53-68.
4. Fu L.M. Integration of neural heuristics into knowledge-based inference. Connection Science. 1:1989;325-340.
5. Fu, L.M. (1991). Rule learning by searching on adapted nets. Proceedings of the Ninth National Conference on Artificial Intelligence (pp. 590-595).
6. Gallant S.I. Connectionist expert systems. Communications of the ACM. 31:1988;152-169.
7. Hayashi Y. A neural expert system with automated extraction of fuzzy if-then rules and its application to medical diagnosis. Lippmann R.P., Moody J.E., Touretzky D.S. Advances in neural information processing systems. 3:1990;578 Kaufmann (Morgan), San Mateo, CA.
8. Hinton G.E. Connectionist learning procedures. Artificial Intelligence. 40:1989;185-234.
9. Holland J.H., Holyoak K.J., Nisbett R.E., Thagard P.R. Induction: processes of inference, learning, and discovery. 1986;MIT Press, Cambridge, MA.
10. Jacobs R.A., Jordan M.I., Nowlan S.J., Hinton G.E. Adaptive mixtures of local experts. Neural Computation. 3:1991;79-87.
11. Jordan, M.I. (1998). Personal communication.
12. Mangasarian O.L., Wolberg W.H. Cancer diagnosis via linear programming. SIAM News. 23:(5):1990;18.
13. McMillan C., Mozer M.C., Smolensky P. Rule induction through integrated symbolic and subsymbolic processing. Moody J.E., Hanson S.J., Lippmann R.P. Advances in neural information processing systems. 4:1991;969 Kaufmann (Morgan), San Mateo, CA.
14. McMillan, C. (1992). Rule induction in a neural network through integrated symbolic and subsymbolic processing. Unpublished Ph.D. Thesis. Department of Computer Science, University of Colorado, Boulder, CO.
15. Minsky, M. (1991). Logical versus analogical or symbolic versus connectionist or neat versus scruffy. AI Magazine, Summer 1991, pp. 35-51.
16. Mozer M.C., Smolensky P. Skeletonization: atechnique for trimming the fat from a network via relevance assessment. Touretzky D.S. Advances in neural information processing Systems. 1:1988;107 Kaufmann (Morgan), San Mateo, CA.
17. Murphy, P.M., Aha, D.W. (1994). UCI repository of machine learning databases. [Machine-readable data repository.] Irvine, CA: University of California, Department of Information and Computer Science. Monks data courtesy of Sebastian Thrun, promoters data courtesy of M. Noordewier, J. Shavlik, congressional voting data courtesy of Jeff Schlimmer, breast cancer data courtesy of Dr William H. Wolberg.
18. Neal, R. (1991). Unpublished doctoral dissertation.
19. Nowlan S.J., Hinton G.E. Adaptive soft weight tying using gaussian mixtures. Moody J.E., Hanson S.J., Lippmann R.P. Advances in neural information processing systems. 4:1991;993 Kaufmann (Morgan), San Mateo, CA.
20. Rumelhart D.E., Hinton G.E., Williams R.J. Learning internal representations by error propagation. Rumelhart D.E., McClelland J.L., The PDP Research Group. Parallel distributed processing: explorations in the microstructure of cognition. 1:1986;318 MIT Press, Cambridge, MA. Foundations.
21. Sejnowski T.J., Rosenberg C.R. Parallel networks that learn to pronounce English text. Complex Systems. 1:1987;145-168.
22. Sun R. Connectionist models of rule-based reasoning. Proceedings of the Thirteenth Annual Conference of the Cognitive Science Society. 1991;Erlbaum (Laurence), Hilsdale, NJ. pp. 437-442.
23. Thrun, S.B. and 23 other authors (1991). The MONK's problems - a performance comparison of different learning algorithms. Technical Report CS-CMU-91-197. Carnegie Mellon University, Pittsburgh, PA.
24. Touretzky D.S., Hinton G.E. A distributed connectionist production system. Cognitive Science. 12:1998;423-466.
25. Towell, G. (1991). Symbolic knowledge and neural networks: Insertion, refinement and extraction. Ph.D. Thesis. Department of Computer Science, University of Wisconsion, Madison, WI.
26. Towell G., Shavlik J.W. Interpretation of artificial neural networks: mapping knowledge-based neural networks into rules. Moody J.E., Hanson S.J., Lippmann R.P. Advances in neural information processing systems. 4:1991;977 Kaufmann (Morgan), San Mateo, CA.