Equivalence between RAM-based neural networks and probabilistic automata

IEEE Transactions on Neural Networks

Volumn 16, Issue 4, 2005, Pages 996-999

  de Souto, Marcilio C P ^a   Ludermir, Teresa B ^b   de Oliveira, Wilson R ^c  

^a FEDERAL UNIVERSITY OF RIO GRANDE DO NORTE   (Brazil)

^b FEDERAL UNIVERSITY OF PERNAMBUCO   (Brazil)

^c UNIVERSIDADE FEDERAL RURAL DE PERNAMBUCO   (Brazil)

Author keywords

Automata theory; Computability; P random access memory (RAM) node; Probabilistic automata; RAM based neural networks; Weightless neural networks (WNNs)

Indexed keywords

AUTOMATA THEORY; COMPUTABILITY AND DECIDABILITY; EQUIVALENCE CLASSES; LEARNING ALGORITHMS; PROBABILISTIC LOGICS; RANDOM ACCESS STORAGE;

PROBABILISTIC AUTOMATA; PROBABILISTIC RECOGNITION ALGORITHM; WEIGHTLESS NEURAL NETWORKS;

NEURAL NETWORKS;

ALGORITHM; ARTIFICIAL NEURAL NETWORK; AUTOMATED PATTERN RECOGNITION; COMPARATIVE STUDY; COMPUTER SIMULATION; EVALUATION; LETTER; METHODOLOGY; STATISTICAL MODEL;

ALGORITHMS; COMPUTER SIMULATION; MODELS, STATISTICAL; NEURAL NETWORKS (COMPUTER); PATTERN RECOGNITION, AUTOMATED;

EID: 23044501856     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2005.849838     Document Type: Article

References (23)

1. I. Aleksander and H. Morton, An Introduction to Neural Computing, 2nd ed. London, U.K.: Chapman & Hall, 1995.
2. T. B. Ludermir, A. C. P. L. F. de Carvalho, A. P. Braga, and M. C. P. de Souto, "Weightless neural models: A review of current and past works," Neural Comput. Surv., vol. 2, pp. 41-61, 1999.
3. I. Aleksander and H. Morton, "General neural unit: Retrieval performance," Electron. Lett., vol. 27, pp. 1776-1778, 1991.
4. D. Gorse and J. G. Taylor, "Enconding temporal structure in probabilistic RAM networks," in Proc. Inst. Elect. Eng. Int. Conf. Neural Networks, 1991, pp. 369-372.
5. P. J. L. Adeodato and J. G. Taylor, "Recurrent neural networks with pRAM's," in Proc. Int. Conf. Artificial Neural Networks (ICANN'95), Paris, France, pp. 607-611.
6. C. Browne and I. Aleksander, "Digital general units with controlled transition probabilities," Electron. Lett., vol. 32, no. 9, pp. 824-825, 1996.
7. M. C. P. de Souto, P. J. L. Adeodato, and T. B. Ludermir, "Sequential RAM-based neural networks: Learnability, generalization, rule extraction, and grammatical inference," Int. J. Neural Syst., vol. 2, pp. 203-210, 1999.
8. G. G. Lockwood and I. Aleksander, "Predicting the behavior of G-RAM networks," Neural Netw., vol. 16, no. 1, pp. 91-100, 2003.
9. K. S. Fu, Syntactic Pattern Recognition and Applications. Englewood Cliffs, NJ: Prentice-Hall, 1982.
10. M. C. P. de Souto, T. B. Ludermir, and M. A. Campos, "Encoding of probabilistic automata in RAM-based networks," in Proc. Int. Joint Conf. Neural Networks, 2000, pp. 439-444.
11. D. Gorse and J. G. Taylor, "A continuous input RAM-based stochastic neural model," Neural Netw., vol. 4, pp. 657-665, 1991.
12. C. D. Manning and H. Schutze, Foundations of Statistical Natural Language Processing. Cambridge, MA: MIT Press, 1999.
13. A. Stolcke and S. M. Omohundro. (1994) Best-first model merging for hidden markov model induction, Berkeley, CA. [Online]. Available: citeseer, ist.psu.edu/stolcke94bestfirst.html
14. D. Gorse, D. A. Romano-Critchley, and J. G. Taylor, "A pulse-based reinforcement algorithm for learning continuous functions," Neuro-comput., vol. 14, no. 4, pp. 319-344, 1997.
15. B. J. Ross, "Probabilistic pattern matching and the evolution of stochastic regular expressions," Appl. Intell., vol. 13, no. 2, pp. 285-300, 2000.
16. L. A. C. Garcia and M. C. P. de Souto, "Global optimization methods for choosing the connectivity pattern of n-tuple classifiers," in Proc. IEEE Int. Joint Conf. Neural Networks, vol. III, Budapest, Hungary, 2004, pp. 2263-2266.
17. A. Yamazaki, T. B. Ludermir, and M. C. P. de Souto, "Global optimization methods for designing neural networks," in Proc. VII Brazilian Symp. Neural Network, vol. 1, Brazil, 2002, pp. 136-141.
18. D. Goldberg, "What every computer scientist should know about floating-point," in ACM Comput. Surv., vol. 23, 1991, pp. 5-48.
19. R. E. Moore, Methods and Applications of Interval Analysis. Philadelphia, PA: SIAM, 1979.
20. R. Hammer, M. Neaga, and D. Ratz, "PASCAL-XSC," in New Concepts for Scientific Computation and Numerical Data Processing. New York: Academic, 1992, pp. 15-44.
21. J. C. M. Oliveira, M. C. P. de Souto, and T. B. Ludermir, "Implementation of probabilistic automata in weightless neural networks," in Proc. VII Brazilian Symp. Neural Networks, 2002, p. 234.
22. W. Maass and E. D. Sontag, "Analog neural nets with Gaussian or other common noise distributions cannot recognize arbitrary regular languages," Neural Computat., vol. 11, pp. 771-782, 1997.
23. J. F. Kolen, "Fool's gold: extracting finite state machines from recurrent network dynamcis," in Advances in Neural Networks Information Processing Systems 6, J. D. Cowan, G. Tesauro, and J. Alspector, Eds. San Mateo, CA: Morgan Kaufmann, 1994, pp. 501-508.