Investigación

 

Evolutionary Associative Memories Through Genetic Programming

 

J. Villegas–Cortez, J.H. Sossa, C. Avilés–Cruz, G. Olague

 

Universidad Autónoma Metropolitana – Azcapotzalco, Departamento de Electrónica, Av. San Pablo 180 Col. Reynosa, México, D.F., 02200, México, e–mail: juanvc@correo.azc.uam.mx

Centro de Investigación en Computación del Instituto Politécnico Nacional, Av. Juan de Dios Bátiz, esquina con Miguel Othón de Mendizábal, Col. Nueva Industrial Vallejo. México D.F. 07738, México, e–mail: hsossa@cic.ipn.mx

Universidad Autónoma Metropolitana – Azcapotzalco, Departamento de Electrónica, Av. San Pablo 180 Col. Reynosa, México D.F., 02200, México.

Centro de Investiación Científica y de Educación Superior de Ensenada CICESE, Km. 107 Carretera Tijuana–Ensenada, Ensenada, 22860, B.C. México.

 

Recibido el 23 de octubre de 2009
Aceptado el 10 de enero de 2010

 

Abstract

Associative Memories (AMs) are useful devices designed to recall output patterns from input patterns. Each input–output pair forms an association. Thus, AMs store associations among pairs of patterns. An important feature is that since its origins AMs have been manually designed. This way, during the last 50 years about 26 different models and variations have been reported. In this paper, we illustrate how new models of AMs can be automatically generated through Genetic Programming (GP) based methodology. In particular, GP provides a way to successfully facilitate the search for an AM in the form of a computer program. The efficiency of the proposal was conducted by means of two tests based on binary and real–valued patterns. The experimental results show that it is possible to automatically generate AMs that achieve good results for the selected pattern recognition problems. This opens a new research area that allows, for the first time, synthesizing new AMs to solve specific problems.

Keywords: Computer science and technology; neural engineering; image quality; contrast; resolution; noise; image analysis.

 

Resumen

Las memorias asociativas (AMs) son estructuras matemáticas específicamente diseñadas para recuperar patrones de entrada con patrones de salida. Cada par asociado (entrada–salida) forma una asociación, es así que la AM almacena las asociaciones entre los pares. Desde sus orígenes las AMs han sido diseñadas manualmente, y durante los últimos 50 años se han reportado un aproximado de 26 modelos de AMs con sus variantes. En este trabajo mostramos un nuevo modelo de AMs que es generado de forma automática por medio de Programación Genética. Este trabajo abre una nueva área de investigación que permite por primera vez sintetizar nuevas AMs para resolver problemas específicos. Para probar la eficiencia de nuestra propuesta la hemos aplicado para los casos de patrones en valores binarios y reales. Los experimentos muestran que es posible la generación automática de AMs para alcanzar buenos resultados para algunos problemas comunes del área de reconocimiento de patrones.

Descriptores: Ciencias de la computación y tecnología; ingeniería neuronal; calidad de imagen; contraste; resolución; ruido; análisis de imagenes.

 

PACS: 89.20.Ff; 87.80.Xs; 87.57.Ce; 87.57.Nk

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

Acknowledgements

The Authors thank SIP–IPN for the economical support under grant number 20100468. Authors thank the European Union, the European Commission and CONACYT for the economical support. This paper has been prepared by economical support of the European Commission under grant FONCI–CYT 93829. The content of this paper is an exclusive responsibility of the CIC–IPN and it cannot be considered that it reflects the position of the European Union. We thank also the reviewers for their comments for the improvement of this paper.

  

References

1. S. Cagnoni, E. Lutton, and G. Olague. Genetic and Evolutionary Computation for Image Processing and Analysis, of EURASIP Book Series on Signal Processing and Communications Series vol. 8 (Hindawi Publishing Corporation, 2008).         [ Links ]

2. Goh, Chi–Keong and Tan, and Kay Chen, IEEE Transactions on Evolutionary Computation 13 (2009) 103.         [ Links ]

3. N. Barricelli, Methodos (1954) 45.         [ Links ]

4. B.A. Garro, H. Sossa, and R.A. Vázquez, International Joint Conference on Neural Networks (IJCNN 2009, Atlanta, GE, USA.) p. 938.         [ Links ]

5. J.H. Holland, Adaptation in natural and artificial systems (University of Michigan Press, 1975).         [ Links ]

6. J.J. Hopfield, Proceedings of the National Academy of Sciences 79 (1982) 2554.         [ Links ]

7. T. Kohonen, IEEE Transactions on Computers C–21 (1972) 353.         [ Links ]

8. J.R. Koza, Genetic Programming: On the Programming of Computers by Means of Natural Selection (MIT Press. 1992).         [ Links ]

9. R. Forsyth, Kybernetes 10 (1981) 159.         [ Links ]

10. B. Hernandez, G. Olague, R. Hammoud, L. Trujillo, and E. Romero, Comput. Vis. Image Underst 106 (2007) 258.         [ Links ]

11. Potter and A. Mitchell, and Jong., Kenneth A. De. Evolutionary Computation 8 (2000) 1.         [ Links ]

12. C. Perez, and G. Olague, Learning Invariant Region Descriptor Operators with Genetic Programming and the F–Measure (International Conference on Pattern Recognition. ICPR., 2008).         [ Links ]

13. D. Rivero, J. Rabunal, and Alejandro Pazos, Automatic Desing of ANNs by Means of GP for Data Mining Tasks: Iris Flower Classification Problem. ICANNGA 07. Part I, Springer–Verlag LNCS4431: (2007)276.         [ Links ]

14. G.X. Ritter et al., IEEE Transactions on Neural Networks 9 (1998)281.         [ Links ]

15. G.X. Ritter et al., International Journal of Mathematical Imaging and Vision 19 (2003) 95.         [ Links ]

16. Shi Guoyong, International Journal of Systems Science 28 (1997)133.         [ Links ]

17. S. Silva and J. Almeida, GPLAB– A Genetic Programming Toolbox for MATLAB. In Gregersen L (ed), Proceedings of the Nordic MATLAB Conference (2003) 278.         [ Links ]

18. M. Quintana, R. Poli, and E. Claridge, Genetic Programming and Evolvable Machines 7 (2006) 81.         [ Links ]

19. I. Rechenberg, Evolutionsstrategie Optimierung technischer Systeme nach Prinzipien der biologischen Evolution (PhD thesis, Reprinted by Fromman–Holzboog. Berlin, Germany, 1973).         [ Links ]

20. A.R. Silva Lavalle, Un Método de Algoritmos Genéticos para Optimizacion de Memorias Asociativas Morfológicas (Tesis. Univesidad de Puerto Rico. 2006).         [ Links ]

21. K. Seo and S. Hyun, Applications of Evolutionary Computation, LNCS 6024 (2010) 352.         [ Links ]

22. H. Sossa, R. Barron and R.A. Vázquez, New associative memories for recall real–valued patterns. LNCS, 3287 (2004) 195.         [ Links ]

23. H. Sossa and R. Barrón, Rev. Mex. Fís. 53 (2007) 10.         [ Links ]

24. K. Steinbuch and Die Lernmatrix, Biological Cybernetics 1 (1961)36.         [ Links ]

25. P. Sussner, Journal of mathematical imaging and vision 19 (2003)81.         [ Links ]

26. K. Trist, V. Ciesielski, and P. Barile, Arts and Technology 262 (2010)255.         [ Links ]

27. L. Trujillo and G. Olague, Using Evolution to Learn How to Perform Interest Point Detection ICPR. (2006) pp. 211.         [ Links ]

28. L. Trujillo and G. Olague, Evolutionary Computation. MIT Press 16 (2008) 483.         [ Links ]

29. G. Olague and C. Puente, Honeybees as an Intelligent based Approach for 3D Reconstruction (International Conference on Pattern Recognition. Hong Kong, China. 2006).         [ Links ]

30. A. Asunción and D.J. Newman, UCI Machine Learning Repository (2007).         [ Links ]

31. R.A. Vázquez and H. Sossa, A New Model of Associative Memories Network. Third International Workshop on Artificial Networks and Intelligent Information Processing (ANNIP, Angers, France, May 2007) p. 9.         [ Links ]

32. R.A. Vázquez and H. Sossa, Hetero–Associative Memories for Voice Signal and Image Processing (CIARP '08: Proceedings of the 13th Iberoamerican Congress on Pattern Recognition, 2008) p. 659.         [ Links ]

33. J. Villegas–Cortez, H. Sossa, C. Avilés, and G. Olague, Advances in Computer Science and Engineering 42 (2009) 91.         [ Links ]

34. C. Yáñez M. and J.L. Diaz de León, Ph. D. Thesis abstract. Computación y Sistemas 6 (2003) 300.         [ Links ]

35. M. Zhang, P. Andreae, and M. Pritchard, Applications of Evolutionary Computing (2003) 455.         [ Links ]

36. U. Bhowan, M. Zhang, and M. Johnston, Genetic Programming for Classification with Unbalanced Data (2010) 1.         [ Links ]

37. X. Yao, Proceedings of the IEEE 87 (1999) 1423.         [ Links ]