DC Element | Wert | Sprache |
dc.contributor.author | Toutounji, Hazem | |
dc.contributor.author | Schumacher, Johannes | |
dc.contributor.author | Pipa, Gordon | |
dc.date.accessioned | 2021-12-23T16:12:53Z | - |
dc.date.available | 2021-12-23T16:12:53Z | - |
dc.date.issued | 2015 | |
dc.identifier.issn | 08997667 | |
dc.identifier.uri | https://osnascholar.ub.uni-osnabrueck.de/handle/unios/10316 | - |
dc.description.abstract | Supplementing a differential equation with delays results in an infinite-dimensional dynamical system. This property provides the basis for a reservoir computing architecture, where the recurrent neural network is replaced by a single nonlinear node, delay-coupled to itself. Instead of the spatial topology of a network, subunits in the delay-coupled reservoir are multiplexed in time along one delay span of the system. The computational power of the reservoir is contingent on this temporal multiplexing. Here, we learn optimal temporal multiplexing by means of a biologically inspired homeostatic plasticity mechanism. Plasticity acts locally and changes the distances between the subunits along the delay, depending on how responsive these subunits are to the input. After analytically deriving the learning mechanism, we illustrate its role in improving the reservoir's computational power. To this end, we investigate, first, the increase of the reservoir's memory capacity. Second, we predict a NARMA-10 time series, showing that plasticity reduces the normalized root-mean-square error by more than 20%. Third, we discuss plasticity's influence on the reservoir's input-information capacity, the coupling strength between subunits, and the distribution of the readout coefficients. | |
dc.description.sponsorship | State of Lower Saxony, Germany, via the University of Osnabruck,; European project PHOCUS in the Framework Information and Communication Technologie [240763]; The contributions of Marcel Nonnenmacher and Anna-Birga Ostendorf to early stages of this work are gratefully acknowledged, as are the fruitful discussions with the members of the PHOCUS consortium. We acknowledge the financial support of the State of Lower Saxony, Germany, via the University of Osnabruck, and the European project PHOCUS in the Framework Information and Communication Technologie (FP7-ICT-2009-C/proposal 240763). | |
dc.language.iso | en | |
dc.publisher | MIT PRESS | |
dc.relation.ispartof | NEURAL COMPUTATION | |
dc.subject | COMPUTATION | |
dc.subject | Computer Science | |
dc.subject | Computer Science, Artificial Intelligence | |
dc.subject | FADING MEMORY | |
dc.subject | MODEL | |
dc.subject | NETWORKS | |
dc.subject | Neurosciences | |
dc.subject | Neurosciences & Neurology | |
dc.subject | PATTERN | |
dc.subject | RATES | |
dc.subject | SELECTIVITY | |
dc.subject | TIME | |
dc.title | Homeostatic Plasticity for Single Node Delay-Coupled Reservoir Computing | |
dc.type | journal article | |
dc.identifier.doi | 10.1162/NECO_a_00737 | |
dc.identifier.isi | ISI:000354652200001 | |
dc.description.volume | 27 | |
dc.description.issue | 6 | |
dc.description.startpage | 1159 | |
dc.description.endpage | 1185 | |
dc.identifier.eissn | 1530888X | |
dc.publisher.place | ONE ROGERS ST, CAMBRIDGE, MA 02142-1209 USA | |
dcterms.isPartOf.abbreviation | Neural Comput. | |
dcterms.oaStatus | Green Published | |
crisitem.author.dept | Institut für Kognitionswissenschaft | - |
crisitem.author.deptid | institute28 | - |
crisitem.author.orcid | 0000-0002-3416-2652 | - |
crisitem.author.parentorg | FB 08 - Humanwissenschaften | - |
crisitem.author.grandparentorg | Universität Osnabrück | - |
crisitem.author.netid | PiGo340 | - |