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

Makarov VA, Song Y, Velarde MG, Hübner D, Cruse H (2008)
Biological Cybernetics 98(5): 371-395.

Zeitschriftenaufsatz | Veröffentlicht | Englisch
 
Download
Es wurde kein Volltext hochgeladen. Nur Publikationsnachweis!
Autor/in
; ; ; ;
Abstract / Bemerkung
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.
Stichworte
situation model; recurrent neural network; memory; learning; Animals; Artificial Intelligence; Computer Simulation; Humans; Models; Neurological; Neural Networks (Computer); Nonlinear Dynamics; Synapses
Erscheinungsjahr
2008
Zeitschriftentitel
Biological Cybernetics
Band
98
Ausgabe
5
Seite(n)
371-395
ISSN
0340-1200
eISSN
1432-0770
Page URI
https://pub.uni-bielefeld.de/record/1588457

Zitieren

Makarov VA, Song Y, Velarde MG, Hübner D, Cruse H. Elements for a general memory structure: properties of recurrent neural networks used to form situation models. Biological Cybernetics. 2008;98(5):371-395.
Makarov, V. A., Song, Y., Velarde, M. G., Hübner, D., & Cruse, H. (2008). Elements for a general memory structure: properties of recurrent neural networks used to form situation models. Biological Cybernetics, 98(5), 371-395. doi:10.1007/s00422-008-0221-5
Makarov, V. A., Song, Y., Velarde, M. G., Hübner, D., and Cruse, H. (2008). Elements for a general memory structure: properties of recurrent neural networks used to form situation models. Biological Cybernetics 98, 371-395.
Makarov, V.A., et al., 2008. Elements for a general memory structure: properties of recurrent neural networks used to form situation models. Biological Cybernetics, 98(5), p 371-395.
V.A. Makarov, et al., “Elements for a general memory structure: properties of recurrent neural networks used to form situation models”, Biological Cybernetics, vol. 98, 2008, pp. 371-395.
Makarov, V.A., Song, Y., Velarde, M.G., Hübner, D., Cruse, H.: Elements for a general memory structure: properties of recurrent neural networks used to form situation models. Biological Cybernetics. 98, 371-395 (2008).
Makarov, Valeri A., Song, Yongli, Velarde, Manuel G., Hübner, David, and Cruse, Holk. “Elements for a general memory structure: properties of recurrent neural networks used to form situation models”. Biological Cybernetics 98.5 (2008): 371-395.

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

Quellen

PMID: 18350312
PubMed | Europe PMC

Suchen in

Google Scholar