Artículos

 

Autómatas celulares alfa-beta

 

Alpha-Beta Cellular Automata

 

Benjamín Luna Benoso y Cornelio Yáñez Márquez

 

Centro de Investigación en Computación, Instituto Politécnico Nacional, D.F., México. Correo: mobius_95@hotmail.com, coryanez@gmail.com

 

Artículo recibido el 04/10/2011.
Aceptado el 07/11/2011.

 

Resumen

Los autómatas celulares Alfa-Beta constituyen un puente conceptual entre dos áreas de investigación que han sido ajenas hasta el día de hoy: las memorias asociativas Alfa-Beta, por un lado, y los autómatas celulares, por el otro. Con los resultados de este artículo es posible aplicar las herramientas propias de las memorias asociativas Alfa-Beta en el ámbito de los autómatas celulares y, viceversa, se puede aplicar el bagaje teórico de los autómatas celulares en los algoritmos propios de las memorias asociativas Alfa-Beta. Al aplicar los autómatas celulares Alfa-Beta en la clasificación de dígitos escritos a mano tomados de la base de datos MNIST del NIST (National Institute of Standars and Technology), los resultados son competitivos al compararlos con otros algoritmos.

Palabras Clave: Autómatas celulares, reconocimiento de patrones, memorias asociativas Alfa-Beta.

 

Abstract

Alpha-Beta Cellular Automata arise as a conceptual bridge between two research areas which have remained disjoint to this day: Alpha-Beta associative memories on one hand and cellular automata on the other hand. The results presented in this work make it possible to apply tools developed on the basis of the Alpha-Beta associative models to the field of cellular automata and vice versa: one can use the theoretical body of cellular automata in applications of the Alpha-Beta associative models. Specifically, the proposed model is applied to the task of classification on the MNIST database of handwritten digits as published by the US National Institute of Standards and Technology (NIST). The results are competitive when compared to those given by other algorithms applied to the same database.

Keywords: Cellular automata, pattern recognition, Alpha-Beta associative memories.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

Agradecimientos

Los autores agradecen al Instituto Politécnico Nacional (Secretaría Académica, COFAA, SIP, ESCOM y CIC), al CONACYT, y SNI por su apoyo económico para el desarrollo de este trabajo. Específicamente al Proyecto SIP-20110661.

 

Referencias

1. Acevedo-Mosqueda, M.E., Yáñez-Márquez, C., & López-Yáñez, I. (2007). Alpha-Beta Bidirectional Associative Memories: Theory and Applications. Neural Processing Letters, 26(1), 1–40.         [ Links ]

2. Amari, S.I. (1972). Learning patterns and pattern sequences by self-organizing nets of threshold elements. IEEE Transactions on Computers, C-21(11), 197–206.         [ Links ]

3. Baffetta, F., Fattorini, L., Franceschi, S., & Corona, P. (2009). Design-based approach to k-nearest neighbours technique for coupling field and remotely sensed data in forest surveys. Remote Sensing of Environ ment, 113(3), 463–475.         [ Links ]

4. Chang, Y.C., Chen, S.M., & Liau, C.J. (2008). Multilabel text categorization based on a new linear classifier learning method and a category-sensitive refinement method. Expert Systems with Applications: An International Journal, 34 (3), 1948–1953.         [ Links ]

5. Chen, F.F. & Chen, F.Y. (2009). Complex dynamics of cellular automata rule 119. Physica A: Statistical Mechanics and its Applications, 388(6), 984–990.         [ Links ]

6. Duda, R.O., Hart P.E., & Stork, D.G. (2001). Pattern Classification (2nd Ed.). New York: Wiley.         [ Links ]

7. Flores, R. (2006). Memorias Asociativas alfa-beta basadas en el código Johnson-Mobiüs Modificado. Tesis de maestría, Centro de Investigación en Computación del Instituto Politécnico Nacional. México, D.F.         [ Links ]

8. Hopfield, J.J. (1982). Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences, 79(8), 2554–2558.         [ Links ]

9. Kosko, B. (1988). Bidirectional associative memories. IEEE Transactions on Systems, Man, and Cybernetics, 18(1), 49–60.         [ Links ]

10. Kostin, A. (2006). A simple and fast multi-class piecewise linear pattern classifier. Pattern Recognition, 39(11), 1949–1962.         [ Links ]

11. Krane, M.J., Johnson, D.R., & Raghavan, S. (2009). The development of a cellular automaton-finite volume model for dendritic growth. Applied Mathematical Modelling, 33(5), 2234–2247.         [ Links ]

12. LeCun, Y. & Cortes, C. (s.f.). The MNIST database of handwritten digits. Retrieved from http://yann.lecun.com/exdb/mnist/.         [ Links ]

13. Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P.(1998). Gradient-Based Learning Applied to Document Recognition. Proceedings of the IEEE, 86(11), 2278–2324.         [ Links ]

14. Luna-Benoso, B., Yáñez-Márquez, C., Figueroa-Nazuno, J., & López-Yáñez, I. (2007). Cellular Mathematical Morphology. Sixth Mexican International Conference on Artificial Intelligence- Special Session (MICAI 2007), Aguascalientes, México, 105–112.         [ Links ]

15. Magnussen, S., McRoberts, R.E., & Tomppo, E.O. (2009). Model-based mean square error estimators for k-nearest neighbour predictions and applications using remotely sensed data for forest inventories. Remote Sensing of Environment, 113(3), 476–488.         [ Links ]

16. Nagatani, T. (2009). Traffic states and fundamental diagram in cellular automaton model of vehicular traffic controlled by signals. Physica A: Statistical Mechanics and its Applications, 388(8), 1673–1681.         [ Links ]

17. Neumann, J.V. (1966). Theory of self-reproducing automata. Urbana: University of Illinois Press.         [ Links ]

18. Markert, H., Kaufmann, U., Kayikci, Z.K., & Palm, G., (2009). Neural associative memories for the integration of language, vision and action in an autonomous agent. Neural Networks, 22(2), 134–143.         [ Links ]

19. Reis, E.A, Santos, L.B.L., & Pinho, S.T.R. (2009). A cellular automata model for avascular solid tumor growth under the effect of therapy. Physica A: Statistical Mechanics and its Applications, 388(7), 1303–1314.         [ Links ]

20. Richard, M., Kirkby, K.J., Webb, R.P., & Kirkby, N.F. (2009). Cellular automaton model of cell response to targeted radiation. Applied Radiation and Isotopes, 67(3), 443–446.         [ Links ]

21. Ritter, G.X., Sussner, P., & Díaz-de-León, J.L. (1998). Morphological associative memories. IEEE Transactions on Neural Networks, 9(2), 281–293.         [ Links ]

22. Ryabko, D. (2006). Pattern Recognition for Conditionally Independent Data. The Journal of Machine Learning Research, 7(Apr), 645–664.         [ Links ]

23. Sohn, S.Y. & Shin, H.W. (2007). Experimental study for the comparison of classifier combination methods. Pattern Recognition, 40(1), 33–40.         [ Links ]

24. Steinbuch, K. (1961). Die Lernmatrix. Biologicalcybernetics, 1(1), 36–45.         [ Links ]

25. Willshaw, D.J., Buneman, O.P., & Longuet-Higgins, H.C. (1969). Non-holographic associative memory. Nature, 222, 960–962.         [ Links ]

26. Wolfram, S. (1983). Statistical mechanics of previous term cellular automata. Reviews of Modern Physics , 55(3), 601–644.         [ Links ]

27. Yáñez-Márquez, C., Sánchez-Fernández, L.P., & López-Yáñez, I. (2006). Alpha-Beta Associative Memories for Gray Level Patterns. Third International Symposium on Neural Networks 2006, Lecture Notes in Computer Science, 3971, 818–823.         [ Links ]

28. Zhang, B., Zhang, Y., & Begg, R.K. (2009). Gait classification in children with cerebral palsy by Bayesian approach. Pattern Recognition, 42(4), 581–586.         [ Links ]

29. Zhao, Y. & Teng, S. (2009). Combinatorial and spectral aspects of nearest neighbor graphs in doubling dimensional and nearly-Euclidean spaces. Theoretical Computer Science, 410(11), 1081–1092.         [ Links ]