RT Journal Article
T1 Elements for a general memory structure: properties of recurrent neural networks used to form situation models
A1 Makarov Slizneva, Valeriy
A1 Song, Yongli
A1 Velarde, Manuel G.
A1 Hübner, David
A1 Cruse, Holk
AB 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.
PB Springer Verlag
SN 0340-1200
YR 2008
FD 2008-05
LK https://hdl.handle.net/20.500.14352/50132
UL https://hdl.handle.net/20.500.14352/50132
LA eng
DS Docta Complutense
RD 24 abr 2025