Memorias de investigación
Artículos en revistas:
A Statistical Convergence Application for the Hopfield Networks
Año:2008
Áreas de investigación
  • Inteligencia artificial
Datos
Descripción
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 î 1 ,î 2 , ...,î 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.
Internacional
Si
JCR del ISI
No
Título de la revista
Information Theory & Applications
ISSN
1310-0513
Factor de impacto JCR
0
Información de impacto
Volumen
15
DOI
Número de revista
1
Desde la página
84
Hasta la página
89
Mes
ENERO
Ranking
Esta actividad pertenece a memorias de investigación
Participantes
Grupos de investigación, Departamentos, Centros e Institutos de I+D+i relacionados
  • Creador: Grupo de Investigación: Fundamentos Matemáticos para Soft Computing
  • Departamento: Matemática Aplicada (Facultad de Informática)