Rule extraction from recurrent neural networks using a symbolic machine learning algorithm

ICONIP 1999, 6th International Conference on Neural Information Processing - Proceedings

Volumn 2, Issue , 1999, Pages 712-717

  Vahed, A S ^a   Omlin, C W ^b  

^a UNIVERSITY OF THE WESTERN CAPE   (South Africa)

^b STELLENBOSCH UNIVERSITY   (South Africa)

Author keywords

[No Author keywords available]

Indexed keywords

CLUSTER ANALYSIS; EXTRACTION; FINITE AUTOMATA; LEARNING SYSTEMS; POLYNOMIAL APPROXIMATION; RECURRENT NEURAL NETWORKS;

DETERMINISTIC FINITE STATE AUTOMATA; INPUT/OUTPUT BEHAVIORS; NUMBER OF CLUSTERS; POLYNOMIAL-TIME; RECURRENT STATE; RULE EXTRACTION; SYMBOLIC MACHINE LEARNING; TRAINING SETS;

LEARNING ALGORITHMS;

EID: 85013614605     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICONIP.1999.845683     Document Type: Conference Paper

References (22)

1. R,. Andrews and J, Diederich, eds,, Proceedings of the NIPS'06 Rule. Extraction from TYained Artificial Neural Network Workshop. 1936. Snowmass, Colorado, December 6, 1996.
2. R.. Andrews, J. Diederich, and A. Tickle, "A survey and critique of techniques for extracting rules from trained artificial neural networks," Knowledge-Based Systems, 1995.
3. M. Casey, "The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction," Neural Computation, vol. 8, no. 6, pp. 1135-1178, 1996.
4. A. Clecieiuans, D. Scrvan-Schrcibcr, and J. McClelland, "Finite state automata and simple recurrent recurrent networks," Neural Computation, vol. 1, no. 3, pp. 372-381, 1989.
5. S. Das and M. Mozer, "A unified gradient-descent/clustering architecture for finite state machine induction," in Advances in Neural Information Processing Systems 6 (J. Cowan, G. Tcsauro, and J. Alspector, eds.), (San Francisco, CA), pp. 19-28, Morgan Kaufmann, 1994.
6. J. Elmau, "Finding structure in time," Cognitive Science., vol. 14, pp. 179-211, 1990.
7. L. Fu, "Rule generation from neural networks," IEEE IVansactions on Systems, Man, and Cybernetics, vol. 24, no. 8, pp. 1114-1124, 1981.
8. C. Giles, C. Miller, D. Chen, II, Chen, G. Sun, and Y. Lee, "Learning and extracting finite state automata with second-order recurrent neural networks," Neural Computation, vol, 4, no. 3, p. 380, 1992.
9. F. Gold, "Complexity of automaton identification from given data," Information and Control, vol. 37, pp. 302-320, 1978.
10. M. Golea, "On the complexity of rule-extraction from neural networks and network-querying," tech. rep., Department of Systems Engineering, Australian National University, Canberra, Australia, 1996.
11. J. Hoperoft and J. Ullimm, Introduction to Automata Theory, Languages, and Computation. Reading, MA: Addison-Wesley Publishing Company, Inc., 1979.
12. T. Kohonen, Self Organizing Maps. Berlin, Germany: Springer Verlag, 1995.
13. K. Lang, "Random dfa's can be approximately learned from sparse uniform examples," in Proceedings of the Fifth A CM Workshop on Computational Learning Theory, (Pittsburgh, PA), July 1992.
14. C. Omlin and C. Giles, "Extraction of rules from discrete-time recurrent neural networks," Neural Networks, vol. 9, no. 1, pp. 41-52, 1996.
15. J. Pollack, "The induction of dynamical recognizers," Machine Learning, vol. 7, pp. 227-252, 1991.
16. P. Tino, B. Home, C. Giles, and P, Colling-wood, "Finite state machines and recurrent neural networks-automata and dynamical systems approaches," in Neural Networks and Pattern Recognition (J. Dayhoff and O. Omidvar, eds), pp. 171-220, Academic Press, 1998.
17. P. Tino and J. Sajda, "Learning and extracting initial mealy machines with a modular neural network model," Neural Computation, vol. 7, no. 4, pp. 822-844, 1995.
18. G. G. Towell and J. W. Shavlik, "The extraction of refined rules from knowledge-based neural networks," Machine. Learning, vol. 13, no. 1, pp. 71-101, 1993.
19. B. Trakhenbrot and Y. Barzdin, Finite automata: Behavior and synthesis. Amsterdam: North-Holland, 1973.
20. R. Watrous and G. Kulm, "Induction of finite-state languages using second-order recurrent networks," Neural Computation, vol. 4, no. 3, p. 400, 1992.
21. R. Williams and D. Zipser, "A learning algorithm for continually running fully recurrent neural networks," Neural Computation, vol. 1, pp. 270-280, 1989.
22. Z. Zeng, R. Goodmau, and P, Smyth, "Learning finite state machines with self-clustering recurrent networks," Neural Computation, vol. 5, no, 6, pp. 976-990, 1993.