caa a22 4500 463245547 CHVBK 20180405153324.0 cr unu---uuuuu 170326e20070501xx s 000 0 eng 10.1007/s00422-006-0137-x doi (NATIONALLICENCE)springer-10.1007/s00422-006-0137-x Modelling memory functions with recurrent neural networks consisting of input compensation units: I. Static situations [Elektronische Daten] [Simone Kühn, Wolf-Jürgen Beyn, Holk Cruse] 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. Springer-Verlag, 2007 Kühn Simone Department of Biological Cybernetics, Faculty of Biology, University of Bielefeld, 33501, Bielefeld, Germany aut Beyn Wolf-Jürgen Department of Mathematics, University of Bielefeld, 33501, Bielefeld, Germany aut Cruse Holk Department of Biological Cybernetics, Faculty of Biology, University of Bielefeld, 33501, Bielefeld, Germany aut Biological Cybernetics Springer-Verlag 96/5(2007-05-01), 455-470 0340-1200 96:5<455 2007 96 422 https://doi.org/10.1007/s00422-006-0137-x text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s00422-006-0137-x text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Kühn Simone Department of Biological Cybernetics, Faculty of Biology, University of Bielefeld, 33501, Bielefeld, Germany aut NATIONALLICENCE 700 1- Beyn Wolf-Jürgen Department of Mathematics, University of Bielefeld, 33501, Bielefeld, Germany aut NATIONALLICENCE 700 1- Cruse Holk Department of Biological Cybernetics, Faculty of Biology, University of Bielefeld, 33501, Bielefeld, Germany aut NATIONALLICENCE 773 0- Biological Cybernetics Springer-Verlag 96/5(2007-05-01), 455-470 0340-1200 96:5<455 2007 96 422 Metadata rights reserved Springer special CC-BY-NC licence nationallicence SWISSBIB 463245520 BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer