Modelling memory functions with recurrent neural networks consisting of input compensation units: I. Static situations

Kühn S, Beyn W-J, Cruse H (2007)
Biological Cybernetics 96(5): 455-470.

Journal Article | Published | English

No fulltext has been uploaded

Author
; ;
Abstract
Humans are able to form internal representations of the information they process?_"a capability which enables them to perform many different memory tasks. Therefore, the neural system has to learn somehow to represent aspects of the environmental situation; this process is assumed to be based on synaptic changes. The situations to be represented are various as for example different types of static patterns but also dynamic scenes. How are neural networks consisting of mutually connected neurons capable of performing such tasks? Here we propose a new neuronal structure for artificial neurons. This structure allows one to disentangle the dynamics of the recurrent connectivity from the dynamics induced by synaptic changes due to the learning processes. The error signal is computed locally within the individual neuron. Thus, online learning is possible without any additional structures. Recurrent neural networks equipped with these computational units cope with different memory tasks. Examples illustrate how information is extracted from environmental situations comprising fixed patterns to produce sustained activity and to deal with simple algebraic relations
Publishing Year
ISSN
eISSN
PUB-ID

Cite this

Kühn S, Beyn W-J, Cruse H. Modelling memory functions with recurrent neural networks consisting of input compensation units: I. Static situations. Biological Cybernetics. 2007;96(5):455-470.
Kühn, S., Beyn, W. - J., & Cruse, H. (2007). Modelling memory functions with recurrent neural networks consisting of input compensation units: I. Static situations. Biological Cybernetics, 96(5), 455-470.
Kühn, S., Beyn, W. - J., and Cruse, H. (2007). Modelling memory functions with recurrent neural networks consisting of input compensation units: I. Static situations. Biological Cybernetics 96, 455-470.
Kühn, S., Beyn, W.-J., & Cruse, H., 2007. Modelling memory functions with recurrent neural networks consisting of input compensation units: I. Static situations. Biological Cybernetics, 96(5), p 455-470.
S. Kühn, W.-J. Beyn, and H. Cruse, “Modelling memory functions with recurrent neural networks consisting of input compensation units: I. Static situations”, Biological Cybernetics, vol. 96, 2007, pp. 455-470.
Kühn, S., Beyn, W.-J., Cruse, H.: Modelling memory functions with recurrent neural networks consisting of input compensation units: I. Static situations. Biological Cybernetics. 96, 455-470 (2007).
Kühn, Simone, Beyn, Wolf-Jürgen, and Cruse, Holk. “Modelling memory functions with recurrent neural networks consisting of input compensation units: I. Static situations”. Biological Cybernetics 96.5 (2007): 455-470.
This data publication is cited in the following publications:
This publication cites the following data publications:

6 Citations in Europe PMC

Data provided by Europe PubMed Central.

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
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
Elements for a general memory structure: properties of recurrent neural networks used to form situation models.
Makarov VA, Song Y, Velarde MG, Hubner D, Cruse H., Biol Cybern 98(5), 2008
PMID: 18350312

65 References

Data provided by Europe PubMed Central.

Networks are not 'hidden rules'
Seidenberg MS, Elman JL., Trends Cogn. Sci. (Regul. Ed.) 3(8), 1999
PMID: 10431180
Computational neuroscience.
Sejnowski TJ, Koch C, Churchland PS., Science 241(4871), 1988
PMID: 3045969

JJ, 1999

U, Biol Cybern 79(), 1998

R, J Comp Physiol A 182(), 1988

MA, Neuron 32(), 2001
Synaptic reverberation underlying mnemonic persistent activity.
Wang XJ., Trends Neurosci. 24(8), 2001
PMID: 11476885

AUTHOR UNKNOWN, 0

RJ, Neural Comput 1(), 1989

RJ, Connect Sci 1(), 1989
Multiple paired forward and inverse models for motor control.
Wolpert DM, Kawato M., Neural Netw 11(7-8), 1998
PMID: 12662752
A spiking network model of short-term active memory.
Zipser D, Kehoe B, Littlewort G, Fuster J., J. Neurosci. 13(8), 1993
PMID: 8340815

Export

0 Marked Publications

Open Data PUB

Web of Science

View record in Web of Science®

Sources

PMID: 17211628
PubMed | Europe PMC

Search this title in

Google Scholar