Universidad Complutense de Madrid
E-Prints Complutense

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



Downloads per month over past year

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

[img] PDF
Restringido a Repository staff only


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



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.

Item Type:Article
Uncontrolled Keywords:Recurrent neural network; Situation model; Memory-Learning
Subjects:Medical sciences > Biology > Neurosciences
ID Code:16654
Deposited On:09 Oct 2012 10:06
Last Modified:20 Feb 2019 10:37

Origin of downloads

Repository Staff Only: item control page