Automatic Synthesis of Associative Memories through Genetic Programming: A First Co-evolutionary Approach
Associative Memories (AMs) are mathematical structures specially designed to associate input patterns with output patterns within a single stage. Since the last fifty years all reported AMs have been manually designed. The paper describes a Genetic Programming based methodology able to create a process for the automatic synthesis of AMs. It paves a new area of research that permits for the first time to propose new AMs for solving specific problems. In order to test our methodology we study the application of AMs for real value patterns. The results illustrate that it is possible to automatically generate AMs that achieve good recall performance for problems commonly used in pattern recognition research.
Unable to display preview. Download preview PDF.
- 2.Olague, G., Puente, C.: Honeybees as an intelligent based approach for 3d reconstruction. In: International Conference on Pattern Recognition, Hong Kong, China, August 20-24 (2006)Google Scholar
- 4.Perez, C., Olague, G.: Learning invariant region descriptor operators with genetic programming and the f-measure. In: International Conference on Pattern Recognition (2008)Google Scholar
- 6.Silva, S., Almeida, J.: Gplab-a genetic programming toolbox for matlab (2004), http://gplab.sourceforge.net/
- 7.Vázquez, R.A., Sossa, H.: Hetero-associative memories for voice signal and image processing. In: Iberoamerican Congress on Pattern Recognition, pp. 659–666 (2008)Google Scholar
- 8.Villegas-Cortez, J., Sossa, H., Aviles-Cruz, C., Olague, G.: Automatic synthesis of associative memories by genetic programming, a first approach. Research in Computing Science. Advances in Computer Science and Engineering 42, 91–102 (2009)Google Scholar
- 9.Yao, X.: Evolving artificial neural networks. Proceedings of the IEEE, 1423–1447 (1999)Google Scholar