{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T06:39:47Z","timestamp":1717483187136},"reference-count":53,"publisher":"MIT Press - Journals","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2015,6]]},"abstract":"<jats:p> 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\u2019s computational power. To this end, we investigate, first, the increase of the reservoir\u2019s 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\u2019s influence on the reservoir\u2019s input-information capacity, the coupling strength between subunits, and the distribution of the readout coefficients. <\/jats:p>","DOI":"10.1162\/neco_a_00737","type":"journal-article","created":{"date-parts":[[2015,4,1]],"date-time":"2015-04-01T15:15:02Z","timestamp":1427901302000},"page":"1159-1185","source":"Crossref","is-referenced-by-count":5,"title":["Homeostatic Plasticity for Single Node Delay-Coupled Reservoir Computing"],"prefix":"10.1162","volume":"27","author":[{"given":"Hazem","family":"Toutounji","sequence":"first","affiliation":[{"name":"Neuroinformatics Department, Institute of Cognitive Science, University of Osnabr\u00fcck, 49069 Osnabr\u00fcck, Germany, and Department of Theoretical Neuroscience, Central Institute of Mental Health, Medical Faculty Mannheim of Heidelberg University, 68159 Mannheim, Germany"}]},{"given":"Johannes","family":"Schumacher","sequence":"additional","affiliation":[{"name":"Neuroinformatics Department, Institute of Cognitive Science, University of Osnabr\u00fcck, 49069 Osnabr\u00fcck, Germany"}]},{"given":"Gordon","family":"Pipa","sequence":"additional","affiliation":[{"name":"Neuroinformatics Department, Institute of Cognitive Science, University of Osnabr\u00fcck, 49069 Osnabr\u00fcck, Germany"}]}],"member":"281","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms1476"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1038\/srep03629"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.6.1129"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.02-01-00032.1982"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1109\/TCS.1985.1085649"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms2368"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2558"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1007\/s12530-013-9080-y"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1038\/32176"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.6908"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000402"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1109359109"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-6992-6"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhj132"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-322-96828-9"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1970.10488634"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1177\/1059712311403631"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1162\/089976606775093882"},{"key":"B19","author":"Jaeger H.","year":"2001","journal-title":"The \u201cecho state\u201d approach to analysing and training recurrent neural networks"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1126\/science.1091277"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2007.04.016"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2007.01.006"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1162\/089976601317098501"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1364\/OE.20.003241"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2007.04.020"},{"issue":"23","key":"B26","volume":"3","author":"Lazar A.","year":"2009","journal-title":"Front. Comput. Neurosci."},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2009.03.005"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760407955"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00232"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(00)80169-5"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.0870-13.2013"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.1000260"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1038\/srep00287"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2010.10.003"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1002494"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(03)00255-1"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00149.2006"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.12.020"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40728-4_4"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.15-08-05448.1995"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1038\/78829"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1038\/85147"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2014.00019"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1003512"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1327"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1108\/17563780910982680"},{"key":"B47","first-page":"1050","author":"Verstraeten D.","year":"2006","journal-title":"International Joint Conference on Neural Networks"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1126\/science.1211095"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1007\/BF00288907"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1016\/j.biosystems.2006.09.020"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2007.04.004"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1248"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1002848"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/NECO_a_00737","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:40:50Z","timestamp":1615585250000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/27\/6\/1159-1185\/8082"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6]]},"references-count":53,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2015,6]]}},"alternative-id":["10.1162\/NECO_a_00737"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_00737","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,6]]}}}