Evolutionary Associative Memories Through Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4192

  title =        "Evolutionary Associative Memories Through Genetic
  author =       "J. Villegas-Cortez and J. H. Sossa and 
                 C. Aviles-Cruz and G. Olague",
  year =         "2011",
  journal =      "Revista Mexicana de Fisica",
  volume =       "57",
  number =       "2",
  pages =        "110--116",
  month =        apr,
  email =        "rmf@smf2.fciencias.unam.mx",
  publisher =    "Sociedad Mexicana de Fisica A.C.",
  keywords =     "genetic algorithms, genetic programming, computer
                 science and technology, neural engineering, image
                 quality, contrast, resolution, noise, image analysis",
  ISSN =         "0035001X",
  URL =          "http://www.redalyc.org/src/inicio/ArtPdfRed.jsp?iCve=57019378003",
  broken =       "http://www.doaj.org/doaj?func=openurl&genre=article&issn=0035001X&date=2011&volume=57&issue=2&spage=110",
  URL =          "http://www.redalyc.org/articulo.oa?id=57019378003",
  URL =          "http://www.redalyc.org/pdf/570/57019378003.pdf",
  oai =          "oai:doaj-articles:7e43d5cf78112ddf1a27e6ef60afb3ac",
  bibsource =    "OAI-PMH server at www.doaj.org",
  size =         "7 pages",
  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, synthesising new AMs to solve specific
  abstract =     "Las memorias asociativas (AMs) son estructuras
                 matematicas especificamente disenadas para recuperar
                 patrones de entrada con patrones de salida. Cada par
                 asociado (entrada-salida) forma una asociacion, es asi
                 que la AM almacena las asociaciones entre los pares.
                 Desde sus origenes las AMs han sido disenadas
                 manualmente, y durante los ultimos 50 anos 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 automatica por medio de
                 Programacion Genetica. Este trabajo abre una nueva area
                 de investigacion que permite por primera vez sintetizar
                 nuevas AMs para resolver problemas especificos. 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
                 generacion automatica de AMs para alcanzar buenos
                 resultados para algunos problemas comunes del area de
                 reconocimiento de patrones.",
  notes =        "In english",

Genetic Programming entries for Juan Villegas-Cortez Juan Humberto Sossa Azuela Carlos Aviles-Cruz Gustavo Olague