A Statistical Convergence Application for the Hopfield Networks

Gimenez Martinez, Victor; Sanchez Torrubia, Maria Gloria y Torres Blanc, Carmen (2008). A Statistical Convergence Application for the Hopfield Networks. "Information Theory and Applications", v. 15 (n. 1); pp. 84-88. ISSN 1310-0513.

Descripción

Título: A Statistical Convergence Application for the Hopfield Networks
Autor/es:
  • Gimenez Martinez, Victor
  • Sanchez Torrubia, Maria Gloria
  • Torres Blanc, Carmen
Tipo de Documento: Artículo
Título de Revista/Publicación: Information Theory and Applications
Fecha: 2008
Volumen: 15
Materias:
Palabras Clave Informales: Learning systems, pattern recognition, graph theory, recurrent neural networks.
Escuela: Facultad de Informática (UPM) [antigua denominación]
Departamento: Matemática Aplicada
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img]
Vista Previa
PDF (Document Portable Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (119kB) | Vista Previa

Resumen

When Recurrent Neural Networks (RNN) are going to be used as Pattern Recognition systems, the problem to be considered is how to impose prescribed prototype vectors ctors ξ 1 ,ξ 2 , ...,ξ p , as fixed points. The synaptic matrix W should be interpreted as a sort of sign correlation matrix of the prototypes, In the classical approach. The weak point in this approach, comes from the fact that it does not have the appropriate tools to deal efficiently with the correlation between the state vectors and the prototype vectors The capacity of the net is very poor because one can only know if one given vector is adequately correlated with the prototypes or not and we are not able to know what its exact correlation degree. The interest of our approach lies precisely in the fact that it provides these tools. In this paper, a geometrical vision of the dynamic of states is explained. A fixed point is viewed as a point in the Euclidean plane R2. The retrieving procedure is analyzed trough statistical frequency distribution of the prototypes. The capacity of the net is improved and the spurious states are reduced. In order to clarify and corroborate the theoretical results, together with the formal theory, an application is presented.

Más información

ID de Registro: 2826
Identificador DC: http://oa.upm.es/2826/
Identificador OAI: oai:oa.upm.es:2826
URL Oficial: http://www.foibg.com/ijita/vol15/ijita-fv15.htm
Depositado por: Memoria Investigacion
Depositado el: 19 Abr 2010 11:12
Ultima Modificación: 20 Abr 2016 12:28
  • GEO_UP4
  • Open Access
  • Open Access
  • Sherpa-Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Recolecta
  • InvestigaM
  • Observatorio I+D+i UPM
  • OpenCourseWare UPM