Symbolic knowledge extraction from trained neural networks: A sound approach

Artificial Intelligence

Volumn 125, Issue 1-2, 2001, Pages 155-207

  D'Avila Garcez, A S ^a   Broda, K ^a   Gabbay, D M ^b  

^a IMPERIAL COLLEGE LONDON   (United Kingdom)

^b KING'S COLLEGE LONDON   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

DECISION THEORY; LEARNING ALGORITHMS; LEARNING SYSTEMS; NEURAL NETWORKS;

NEURAL-SYMBOLIC INTEGRATION; NONMONOTONIC REASONING;

KNOWLEDGE ACQUISITION;

EID: 0035127989     PISSN: 00043702     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0004-3702(00)00077-1     Document Type: Article

References (37)

1. Alexander J.A., Mozer M.C. Template-based algorithms for connectionist rule extraction. Tesauro G., Touretzky D., Leen T. Advances in Neural Information Processing Systems (NIPS). 7:1995;MIT Press, Cambridge, MA.
2. Andrews R., Diederich J., Tickle A.B. A survey and critique of techniques for extracting rules from trained artificial neural networks. Knowledge-Based Systems. 8:(6):1995.
3. Andrews R., Geva S. Inserting and extracting knowledge from constrained error backpropagation networks. Proc. 6th Australian Conference on Neural Networks. 1995.
4. d'Avila Garcez A.S., Zaverucha G., da Silva V.N.L. Applying the connectionist inductive learning and logic programming system to power system diagnosis. Proc. IEEE International Joint Conference on Neural Networks, ICNN97. 1997;Houston, TX.
5. d'Avila Garcez A.S., Zaverucha G. The connectionist inductive learning and logic programming system. Applied Intelligence Journal (Special Issue on Neural Networks and Structured Knowledge). 11:(1):1999;59-77.
6. d'Avila Garcez A.S., Broda K., Gabbay D.M. Metalevel priorities and neural networks. Proc. Workshop on the Foundations of Connectionist-Symbolic Integration, ECAI 2000, Berlin, Germany. 2000.
7. Bose N.K., Liang P. Neural Networks Fundamentals with Graphs, Algorithms, and Applications. 1996;McGraw-Hill, New York.
8. Craven M.W., Shavlik J.W. Using sampling and queries to extract rules from trained neural networks. Proc. 11th International Conference on Machine Learning, New Brunswick, NJ. 1994.
9. Craven M.W. Extracting Comprehensible Models from Trained Neural Networks. 1996;University of Wisconsin, Madison, WI.
10. Fu L. Neural Networks in Computer Intelligence. 1994;McGraw-Hill, New York.
11. Gelfond M., Lifschitz V. Classical negation in logic programs and disjunctive databases. New Generation Computing. 9:1991;365-386.
12. Gallant S.I. Neural Networks Learning and Expert Systems. 1993;MIT Press, Cambridge, MA.
13. Hertz J., Krogh A., Palmer R.G. Introduction to the Theory of Neural Computation, Santa Fe Institute. Studies in the Science of Complexity. 1991;Addison-Wesley, Reading, MA.
14. Hilario M. An overview of strategies for neurosymbolic integration. Connectionist-Symbolic Integration: From Unified to Hybrid Approaches - IJCAI-95, Montreal, Que. 1995.
15. Holldobler S., Kalinke Y. Toward a new massively parallel computational model for logic programming. Proc. Workshop on Combining Symbolic and Connectionist Processing, ECAI-94, Amsterdam. 1994.
16. Hornik K., Stinchcombe M., White H. Multilayer feedforward networks are universal approximators. Neural Networks. 2:1989;359-366.
17. Kautz H., Kearns M., Selman B. Horn approximations of empirical data. Artificial Intelligence. 74:1995;129-145.
18. Lavrac N., Dzeroski S. Inductive Logic Programming: Techniques and Applications. Ellis Horwood Series in Artificial Intelligence. 1994;Ellis Horwood, Chichester.
19. Lloyd J.W. Foundations of Logic Programming. 1987;Springer, Berlin.
20. Lozowski A., Zurada J.M. Extraction of linguistic rules from data via neural networks and fuzzy approximation. Cloete I., Zurada J.M. Knowledge-Based Neurocomputing. 2000;403-417 MIT Press, Cambridge, MA.
21. Marek W., Truszczynski M. Nonmonotonic Logic: Context Dependent Reasoning. 1993;Springer, Berlin.
22. Minsky M. Logical versus analogical, symbolic versus connectionist, neat versus scruffy. AI Magazine. 12:(2):1991.
23. Maire F. A partial order for the M-of-N rule extraction algorithm. IEEE Transactions on Neural Networks. 8:(6):1997;1542-1544.
24. Nute D. Defeasible logic. Gabbay D., Hogger C.J., Robinson J.A. Handbook of Logic in Artificial Intelligence and Logic Programming, Vol. 3. 1994;353-396 Oxford Science Publications, Oxford.
25. Prakken H., Sartor G. Argument-based extended logic programming with defeasible priorities. J. Appl. Non-Classical Logic. 7:(1/2):1997;25-75.
26. Pop E., Hayward R., Diederich J. RULENEG: Extracting Rules from a Trained ANN by Stepwise Negation. 1994;QUT NRC.
27. Rumelhart D.E., Hinton G.E., Williams R.J. Learning internal representations by error propagation. Rumelhart D.E., McClelland and the PDP Research Group J.L. Parallel Distributed Processing. 1:1986;MIT Press, Cambridge, MA.
28. Selman B., Levesque H., Mitchell D. A new method for solving hard satisfiability problems. Proc. AAAI-92, San Jose, CA. 1992.
29. Setiono R. A penalty-function for pruning feedforward neural networks. Neural Computation. 9:1997;185-204.
30. Setiono R. Extracting rules from neural networks by pruning and hidden-unit splitting. Neural Computation. 9:1997;205-225.
31. Silva V.N., Zaverucha G., Souza G. An integration of neural networks and nonmonotonic reasoning for power systems diagnosis. Proc. IEEE International Conference on Neural Networks, ICNN-95, Perth, Australia. 1995.
32. Thrun S.B. The MONK's problem: A performance comparison of different learning algorithms. 1991;Technical Report, CMU-CS-91-197, Carnegie Mellon University, Pittsburgh, PA.
33. Thrun S.B. Extracting provably correct rules from artificial neural networks. 1994;Technical Report, Institut für Informatik, Universität Bonn, Bonn.
34. Towell G.G. Symbolic Knowledge and Neural Networks: Insertion, Refinement and Extraction. 1992;Ph.D. Thesis, University of Wisconsin, Madison, WI.
35. Towell G.G., Shavlik J.W. The extraction of refined rules from knowledge based neural networks. Machine Learning. 13:1993.
36. Towell G.G., Shavlik J.W. Knowledge-based artificial neural networks. Artificial Intelligence. 70:1994;119-165.
37. Watson J.D., Hopkins N.H., Roberts J.W., Steitz J.A., Weiner A.M. Molecular Biology of the Gene, Vol. 1. 1987;Benjamin Cummings, Menlo Park, CA.