info presentación miembros líneas investigación publicaciones investigación tesis docencia

[Articulos Revista] [Articulos Congreso] [Reports] [Libros] [Capitulos Libro] [Todo] [Resumen]

Categoria WoS
  • Artificial Neural Networks
  • Genetic Algorithms
Titulo: A New Hybrid Evolutionary Mechanism Based on Unsupervised Learnig for Connectionist Systems
Tipo: revista internacional
Fecha: 6,2007
Revista: Neurocomputing
JCR Journal; Impact Factor: 0.865
Citas ISI: 2 Citas Scopus: 2 Citas Google Scholar: 4
Volumen: 70/16-18
Paginas: 2799-2808
ISSN: 0925-2312
Editorial: Elsevier B. V.


Recent studies have confirmed that the modulation of synaptic efficacy affects emergent behaviour of brain cells assemblies. We report the first results of adding up the behaviour of particular brain circuits to Artificial Neural Networks. A new hybrid learning method has emerged. In order to find the best solution to a given problem, this method combines the use of Genetic Algorithms with particular changes to connection weights based on this behaviour. We show this combination in feed-forward multilayer architectures initially created to solve classification problems and we illustrate the benefits obtained with this new method.

    .: SABIA :.  Sistemas Adaptativos y Bioinspirados en Inteligencia Artificial