We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Elements for a general memory structure: properties of recurrent neural networks used to form situation models.
- Authors
Makarov, Valeri; Song, Yongli; Velarde, Manuel; Hübner, David; Cruse, Holk
- Abstract
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.
- Subjects
BIOLOGICAL neural networks; NEUROTRANSMITTERS; DYNAMICS; SYNAPSES; MATHEMATICAL models; CONVERGENT evolution; COGNITIVE neuroscience
- Publication
Biological Cybernetics, 2008, Vol 98, Issue 5, p371
- ISSN
0340-1200
- Publication type
Article
- DOI
10.1007/s00422-008-0221-5