E-Prints Complutense

Elements for a general memory structure: properties of recurrent neural networks used to form situation models



Último año

Makarov, Valeri A. y Song, Yongli y Velarde, Manuel G. y Hübner, David y Cruse, Holk (2008) Elements for a general memory structure: properties of recurrent neural networks used to form situation models. Biological Cybernetics , 98 (5). 371-395 . ISSN 0340-1200

[img] PDF
Restringido a Sólo personal autorizado del repositorio hasta 31 Diciembre 2020.


URL Oficial: http://www.springerlink.com/content/h3758550745u3617/fulltext.pdf

URLTipo de URL


We study how individual memory items are stored assuming that situations given in the environment can be represented in the form of synaptic-like couplings in recurrent neural networks. Previous numerical investigations have shown that specific architectures based on suppression or max units can successfully learn static or dynamic stimuli (situations). Here we provide a theoretical basis concerning the learning process convergence and the network response to a novel stimulus. We show that, besides learning "simple" static situations, a nD network can learn and replicate a sequence of up to n different vectors or frames. We find limits on the learning rate and show coupling matrices developing during training in different cases including expansion of the network into the case of nonlinear interunit coupling. Furthermore, we show that a specific coupling matrix provides low-pass-filter properties to the units, thus connecting networks constructed by static summation units with continuous-time networks. We also show under which conditions such networks can be used to perform arithmetic calculations by means of pattern completion.

Tipo de documento:Artículo
Palabras clave:Recurrent neural network; Situation model; Memory-Learning
Materias:Ciencias Biomédicas > Biología > Neurociencias
Código ID:16654
Depositado:09 Oct 2012 10:06
Última Modificación:27 Jun 2016 16:40

Descargas en el último año

Sólo personal del repositorio: página de control del artículo