Automatic synthesis of associative memories through genetic programming: a first co-evolutionary approach

Authors:
Juan Villegas-Cortez;Gustavo Olague;Carlos Aviles;Humberto Sossa;Andres Ferreyra
Affiliations:
Departamento de Electrónica, Universidad Autónoma Metropolitana - Azcapotzalco, México, D.F., México;Centro de Investiación Científica y de Educación Superior de Ensenada CICESE, Ensenada, B.C., México;Departamento de Electrónica, Universidad Autónoma Metropolitana - Azcapotzalco, México, D.F., México;Centro de Investigacion en Computacion CIC-IPN, México, D.F., México;Departamento de Electrónica, Universidad Autónoma Metropolitana - Azcapotzalco, México, D.F., México
Venue:
EvoApplicatons'10 Proceedings of the 2010 international conference on Applications of Evolutionary Computation - Volume Part I
Year:
2010

Citing 5
Cited 0

Genetic programming: on the programming of computers by means of natural selection

Genetic programming: on the programming of computers by means of natural selection
Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents

Evolutionary Computation
Honeybees as an Intelligent based Approach for 3D Reconstruction

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 01
Hetero-Associative Memories for Voice Signal and Image Processing

CIARP '08 Proceedings of the 13th Iberoamerican congress on Pattern Recognition: Progress in Pattern Recognition, Image Analysis and Applications
Coevolutionary computation

Artificial Life

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.