SciELO - Scientific Electronic Library Online

 
vol.10 issue1Statistical Characterization and Optimization of Artificial Neural Networks in Time Series Forecasting: The One-Period Forecast Case author indexsubject indexsearch form
Home Pagealphabetic serial listing  

Services on Demand

Journal

Article

Indicators

Related links

  • Have no similar articlesSimilars in SciELO

Share


Computación y Sistemas

Print version ISSN 1405-5546

Comp. y Sist. vol.10 n.1 México Jul./Sep. 2006

 

Resumen de tesis doctoral

 

Alpha–Beta Bidirectional Associative Memories

 

Memorias Asociativas Bidireccionales alfa–beta

 

Graduated: María Elena Acevedo Mosqueda
Centro de Investigación en Computación del IPN
Av. Juan de Dios Bátiz s/n Esq. Miguel Othón de Mendizábal
C.P. 07738 México D.F.
Escuela Superior de Ingeniería Mecánica y Eléctrica del IPN
Av. Instituto Politécnico Nacional s/n
C.P. 07738 México D.F.

e–mail: eacevedo@ipn.mx

Advisor: Cornelio Yáñez Márquez
Centro de Investigación en Computación del IPN
Av. Juan de Dios Bátiz s/n Esq. Miguel Othón de Mendizábal
C.P. 07738 México D.F.

e–mail cyanez@cic.ipn.mx

 

Graduated in September 5, 2006

 

Abstract

Most models of Bidirectional associative memories intend to achieve that all trained pattern correspond to stable states; however, this has not been possible. Also, none of the former models has been able to recall all the trained patterns. In this work we introduce a new model of bidirectional associative memory which is not iterative and has no stability problems. It is based on the Alpha–Beta associative memories. This model allows perfect recall of all trained patterns, with no ambiguity and no conditions. Applications of Alpha–Beta Bidirectional Associative Memories as fingerprint recognition and translator are presented.

Keywords: Bidirectional Associative Memories, Alpha–Beta Associative Memories, correct recall.

 

Resumen

Los modelos de memorias asociativas bidireccionales, en su mayoría, pretenden lograr que todos los patrones entrenados correspondan a estados estables; sin embargo, esto no ha sido posible. Además, ninguno de esos modelos ha podido recuperar todos los patrones entrenados. En este trabajo se presenta un nuevo modelo de memoria asociativa bidireccional que no es iterativo y no tiene problemas de estabilidad; está basado en las memorias asociativas Alfa–Beta. Este modelo permite la recuperación perfecta de todos los patrones entrenados sin ambigüedades y sin condiciones. Se presentan dos ejemplos de aplicación: el primero de reconocimiento de huellas digitales, y el segundo es un traductor.

Palabras clave: Memorias asociativas bidireccionales, memorias asociativas Alfa–Beta, recuperación correcta.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

Referencias

1. Kosko, B., "Bidirectional associative memories", IEEE Transactions on Systems, Man, and Cybernetics, vol. 18, no. 1, (1988) 49–60.        [ Links ]

2. Jeng, Y.–J.; Yeh, C.–C. & Chiveh, T.D., "Exponential bidirectional associative memories", Electronics Letters, Vol. 26, Issue 11, (1990) 717–718.        [ Links ]

3. Wang, W.–J. & Lee, D.–L., "Modified exponential bidirectional associative memories", Electronics Letters, Vol. 28, Issue 9, (1992). 888–890.        [ Links ]

4. Chen, S., Gao, H. & Yan, W., "Improved exponential bidirectional associative memory", Electronics Letters, Vol. 33, Issue 3, (1997) 223–224.        [ Links ]

5. Wang, Y.–F., Cruz J.B., Jr. & Mulligan, Jr., "Two coding strategies for bidirectional associative memory", IEEE Transactions on Neural Networks, Vol. 1, Issue 1, (1990) 81–92.        [ Links ]

6. Wang, Y.–F., Cruz J.B., Jr. & Mulligan, Jr., "Guaranteed recall of all training pairs for bidirectional associative memory", IEEE Transactions on Neural Networks, Vol. 1, Issue 6, (1991) 559–56.        [ Links ]

7. Perfetti, R., "Optimal gradient descent learning for bidirectional associative memories", Electronics Letters, Vol. 29, Issue 17, (1993) 1556–1557.        [ Links ]

8. Zheng, G., Givigi, S.N. & Zheng, W., "A New Strategy for Designing Bidirectional Associative Memories", Lecture Notes in Computer Science, Springer–Verlag, Vol. 3496, (2005) 398–403.        [ Links ]

9. Shen, D. & Cruz, J.B., Jr., "Encoding strategy for maximum noise tolerance bidirectional associative memory", IEEE Transactions on Neural Networks, Vol. 16, Issue 2, (2005) 293–300.        [ Links ]

10. Arik, S., "Global asymptotic stability analysis of bidirectional associative memory neural networks with time delays", IEEE Transactions on Neural Networks, vol. 16, no. 3 (2005) 580–585.        [ Links ]

11. Park, J., "Robust stability of bidirectional associative memory neural networks with time delays", Physics Letters A, vol. 349, (2006) 494–499.        [ Links ]

12. Ritter, G.X., Diaz–de Leon, J.L. & Sussner, P., "Morphological bidirectional associative memories", Neural Networks, Vol. 12, (1999) 851–867.        [ Links ]

13. Wu, Y. & Pados, D.A., "A feed forward bidirectional associative memory", IEEE Transactions on Neural Networks, Vol. 11, Issue 4, (2000) 859–866.        [ Links ]

14. Yánez, C., Memorias Asociativas basadas en Relaciones de Orden y Operadores Binarios, Tesis de Doctorado, Centro de Investigación en Computación, México (2002).        [ Links ]

Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License