Extraction of comprehensive symbolic rules from a multi-layer perceptron

Engineering Applications of Artificial Intelligence

Volumn 9, Issue 2, 1996, Pages 137-143

  Avner, Stéphane ^a  

^a UNIVERSITÉ PIERRE ET MARIE CURIE   (France)

Author keywords

extraction of comprehensible symbolic rules; Learning from examples; neural network interpretation; generalization

Indexed keywords

ALGORITHMS; COGNITIVE SYSTEMS; DATA PROCESSING; KNOWLEDGE ACQUISITION; LEARNING SYSTEMS;

COMPREHENSIVE SYMBOLIC RULES; GENERALIZATION; MULTI-LAYER PERCEPTRON; NEURAL NETWORK INTERPRETATION;

NEURAL NETWORKS;

EID: 0030125175     PISSN: 09521976     EISSN: None     Source Type: Journal    
DOI: 10.1016/0952-1976(96)00004-8     Document Type: Article

References (18)

1. Hanson S. J. and Burr D. J. What connectionist models learn: Learning and representation in connectionist networks. Behavioral and Brain Sciences 13, 471-518 (1990).
2. Rumelhart D. E. and McClelland J. E. Parallel Distributed Processing: Explorations in the Microstructure of Cognition. MIT Press, Cambridge, MA (1986).
3. Beale R. and Jackson T. Neural Computing: An Introduction. Adam Hilger, Bristol (1990).
4. Hertz, J., Krogh, A. and Palmer R. G. Introduction to the Theory of Neural Computation. Adison Wesley, Reading, MA (1991).
5. Chan, L.-W. Analysis of the internal representations in neural networks for machine intelligence. Proc. NintH National Conf. on Artificial Intelligence, Anaheim, CA, pp. 578-583 [1991).
6. Minsky M. L. and Papert S. A. Epilog: the new connectionism. Perceptrons, 3rd edn, pp. 247-280. MIT Press, Cambridge, MA (1988).
7. Denker J., Schwartz D., Wittner B., Solla S., Howard R., Jackel L. and Hopfield J. Large automatic learning, rule extraction, and generalization. Complex Systems 1, 877-922 (1987).
8. Touretzky D. S. and Hinton G. E. Symbols among the Neurons: details of a connectionist inference architecture. Proc. Ninth Int. Joint Conf. on Artificial Intelligence, pp. 238-243 (1985).
9. Sejnowski T. J. and Rosenberg C. R. Parallel networks that learn to pronounce English text. Complex Systems 1 145-168 (1987).
10. Saito K. and Nakano R. Medical diagnostic expert system based on PDP model. Proc. IEEE Int. Conf. on Neural Networks, pp. 255-262 (1988).
11. Gallant S. I. Connectionist expert systems. Communications of the ACM 31 152-169 (1988).
12. Sestito S. and Dillon T. Using multi-layered neural networks for learning symbolic knowledge. Proc. 1990 Australian Artificial Intelligence Conf., Perth, Australia (1990).
13. Fu L,-M. Rule learning by searching on adapted nets, Proc. Ninth National Conf. on Artificial Intelligence, Anaheim, CA, pp. 590-595 (1991).
14. Towell G. and Shavlik J. W. Interpretation of artificial neural networks: mapping knowledge-based neural networks into rules. Advances in Neural Information Processing Systems, Vol. 4 (Moody J. E. et al., Eds). Denver, CO (1991).
15. Barlow H. B. Single units and sensation: a neuron doctrine for perceptual psychology? Perception 1, 371-394 (1972).
16. Langley P. Toward a unified science of machine learning. Machine Learning 3, 253-259 (1989).
17. Le Cun Y., Denker J. S. and Solla S. A. Optimal brain damage. Advances in Neural Information Processing Systems (Touretzky D. S., Ed.), Vol. 2, pp. 598-605 (1989).
18. Mozer, M. C. and Smolensky P. Skeletonization: A technique for trimming the fat from a network via relevance assessment. Advances in Neural Information Processing Systems (Touretzky D. S., Ed.), Vol 1, pp. 107-115 (1988).