Stable Encoding of Large Finite-State Automata in Recurrent Neural Networks with Sigmoid Discriminants

Neural Computation

Volumn 8, Issue 4, 1996, Pages 675-696

  Omlin, Christian W ^a   Giles, C Lee ^a,b  

^a NEC LABORATORIES AMERICA   (United States)

^b UNIVERSITY OF MARYLAND   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; AUTOMATION; COMPUTER PROGRAM; COMPUTER SIMULATION; DISCRIMINANT ANALYSIS; NERVE CELL; RANDOMIZATION;

ALGORITHMS; AUTOMATION; COMPUTER SIMULATION; DISCRIMINANT ANALYSIS; NEURAL NETWORKS (COMPUTER); NEURONS; RANDOM ALLOCATION; SOFTWARE;

EID: 0030585201     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/neco.1996.8.4.675     Document Type: Article

References (17)

1. Alon, N., Dewdney, A., and Ott, T. 1991. Effecient stimulation of finite automata by neural nets. J. Assoc. Computing Mach. 38(2), 495-514.
2. Alquezar, R., and Sanfeliu, A. (1995). An algebraic framework to represent finite state machines in single-layer recurrent neural networks. Neural Comp. 7(5), 931.
3. Elman, J. 1990. Finding structure in time. Cog. Sci. 14, 179-211.
4. Frasconi, P., Gori, M., Maggini, M., and Soda, G. 1991. A unified approach for integrating explicit knowledge and learning by example in recurrent networks. Proc. Int. Joint Conf. Neural Networks 1, 811. IEEE 91CH3049-4.
5. Frasconi, P., Gori, M., and Soda, G. 1993. Injecting Nondeterministic Finite State Automata into Recurrent Networks. Tech. Rep. Dipartimento di Sistemi e Informatica, Università di Firenze, Italy, Florence, Italy.
6. Giles, C., and Omlin, C. 1993. Extraction, insertion and refinement of symbolic rules in dynamically driven recurrent neural networks. Connect. Sci. 5(3 & 4), 307-337.
7. Giles, C., Miller, C., Chen, D., Chen, H., Sun, G., and Lee, Y. 1992. Learning and extracting finite state automata with second-order recurrent neural networks. Neural Comp. 4(3), 380.
8. Gori, M., Maggini, M., and Soda, G. 1996. Insertion of finite state automata in recurrent radial basis function networks. Machine Learning, in press.
9. Hopcroft, J., and Ullman, J. 1979. Introduction to Automata Theory, Languages, and Computation. Addison-Wesley, Reading, MA.
10. Horne, B., and Hush, D. 1994. Bounds on the complexity of recurrent neural network implementations of finite state machines. In Advances in Neural Information Processing Systems 6, J. Cowen, G. Tesauro, and J. Alspector, eds., pp. 359-366. Morgan Kaufmann, San Mateo, CA.
11. Minsky, M. 1967. Computation: Finite and Infinite Machines, Chap. 3, pp. 32-66. Prentice-Hall, Englewood Cliffs, NJ.
12. Omlin, C., and Giles, C. 1995. Constructing Deterministic Finite-state Automata in Sparse Recurrent Neural Networks. Technical Report UMIACS-TR-90 and CS-TR-3460, University of Maryland, College Park, Md.
13. Pollack, J. 1991. The induction of dynamical recognizers. Machine Learning 7, 227-252.
14. Servan-Schreiber, D., Cleeremans, A., and McClelland, J. 1991. Graded state machine: The representation of temporal contingencies in simple recurrent networks. Machine Learning 7, 161.
15. Tino, P. 1994. Private communication.
16. Watrous, R., and Kuhn, G. 1992. Induction of finite-state languages using second-order recurrent networks. Neural Comp. 4(3), 406.
17. Zeng, Z., Goodman, R., and Smyth, P. 1993. Learning finite state machines with self-clustering recurrent networks. Neural Comp. 5(6), 976-990.