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.

Journal Article | Published | English

No fulltext has been uploaded

Author
; ; ; ;
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.
Publishing Year
ISSN
eISSN
PUB-ID

Cite this

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.
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.
This data publication is cited in the following publications:
This publication cites the following data publications:

5 Citations in Europe PMC

Data provided by Europe PubMed Central.

Prediction-for-CompAction: navigation in social environments using generalized cognitive maps.
Villacorta-Atienza JA, Calvo C, Makarov VA., Biol Cybern 109(3), 2015
PMID: 25677525
Neural network architecture for cognitive navigation in dynamic environments.
Villacorta-Atienza JA, Makarov VA., IEEE Trans Neural Netw Learn Syst 24(12), 2013
PMID: 24805224
A hexapod walker using a heterarchical architecture for action selection.
Schilling M, Paskarbeit J, Hoinville T, Huffmeier A, Schneider A, Schmitz J, Cruse H., Front Comput Neurosci 7(), 2013
PMID: 24062682
No need for a cognitive map: decentralized memory for insect navigation.
Cruse H, Wehner R., PLoS Comput. Biol. 7(3), 2011
PMID: 21445233
Compact internal representation of dynamic situations: neural network implementing the causality principle.
Villacorta-Atienza JA, Velarde MG, Makarov VA., Biol Cybern 103(4), 2010
PMID: 20589508

18 References

Data provided by Europe PubMed Central.


AUTHOR UNKNOWN, 0

AUTHOR UNKNOWN, 0

JL, Cogn Sci 14(), 1990

AUTHOR UNKNOWN, 0

JM, 1995
Neural networks and physical systems with emergent collective computational abilities.
Hopfield JJ., Proc. Natl. Acad. Sci. U.S.A. 79(8), 1982
PMID: 6953413
New records and geographic distributions of mosses in Hebei province,China
Li Lin, Wang Xiaorui, Journal of Hebei Normal University (Natural Science) 28(1), 2004
PMID: 189178

T, Mech Mach Theory 37(), 2002

G, 1996

F, Netw: Comput Neural Syst 13(), 2002

U, Biol Cybern 79(), 1998

G, 2003

Export

0 Marked Publications

Open Data PUB

Web of Science

View record in Web of Science®

Sources

PMID: 18350312
PubMed | Europe PMC

Search this title in

Google Scholar