A new hybrid evolutionary mechanism based on unsupervised learning for Connectionist Systems

Ana Porto, Alfonso Araque, Juan Rabuñal, Julián Dorado, Alejandro Pazos

Research output: Contribution to journalArticlepeer-review

14 Scopus citations

Abstract

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.

Original languageEnglish (US)
Pages (from-to)2799-2808
Number of pages10
JournalNeurocomputing
Volume70
Issue number16-18
DOIs
StatePublished - Oct 2007

Bibliographical note

Funding Information:
This work was partially supported by Grants from the Spanish Ministry of Education and Culture (TIC2003-07593), the General Directorate of Research of the Xunta de Galicia (PGIDIT03-PXIC10504PN, PGIDIT04-PXIC10503PN, PGIDIT04-PXIC10504PN), and Grants from A Coruña University (EQUIPOS EN FORMACIÓN-UDC2005), Spain.

Keywords

  • Artificial Neural Networks
  • Brain computational models
  • Connectionist Systems
  • Genetic Algorithms
  • Hybrid learning method

Fingerprint Dive into the research topics of 'A new hybrid evolutionary mechanism based on unsupervised learning for Connectionist Systems'. Together they form a unique fingerprint.

Cite this