A Statistical Convergence Application for the Hopfield Networks

Gimenez Martinez, Victor and Sanchez Torrubia, Maria Gloria and 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.

Description

Title: A Statistical Convergence Application for the Hopfield Networks
Author/s:
  • Gimenez Martinez, Victor
  • Sanchez Torrubia, Maria Gloria
  • Torres Blanc, Carmen
Item Type: Article
Título de Revista/Publicación: Information Theory and Applications
Date: 2008
Volume: 15
Subjects:
Freetext Keywords: Learning systems, pattern recognition, graph theory, recurrent neural networks.
Faculty: Facultad de Informática (UPM)
Department: Matemática Aplicada
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (119kB) | Preview

Abstract

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.

More information

Item ID: 2826
DC Identifier: http://oa.upm.es/2826/
OAI Identifier: oai:oa.upm.es:2826
Official URL: http://www.foibg.com/ijita/vol15/ijita-fv15.htm
Deposited by: Memoria Investigacion
Deposited on: 19 Apr 2010 11:12
Last Modified: 20 Apr 2016 12:28
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM