000873632 001__ 873632 000873632 005__ 20240313094942.0 000873632 020__ $$a978-3-030-30486-7 (print) 000873632 020__ $$a978-3-030-30487-4 (electronic) 000873632 0247_ $$2doi$$a10.1007/978-3-030-30487-4_54 000873632 0247_ $$2ISSN$$a0302-9743 000873632 0247_ $$2ISSN$$a1611-3349 000873632 0247_ $$2WOS$$aWOS:000546494000054 000873632 037__ $$aFZJ-2020-00875 000873632 1001_ $$00000-0002-6855-0012$$aTetko, Igor V.$$b0$$eEditor 000873632 1112_ $$aICANN 2019: Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation pp$$cMunich$$d2019-09-17 - 2019-09-19$$wGermany 000873632 245__ $$aTraining Delays in Spiking Neural Networks 000873632 260__ $$c2019 000873632 3367_ $$0PUB:(DE-HGF)1$$2PUB:(DE-HGF)$$aAbstract$$babstract$$mabstract$$s1593502935_1667 000873632 3367_ $$033$$2EndNote$$aConference Paper 000873632 3367_ $$2BibTeX$$aINPROCEEDINGS 000873632 3367_ $$2DRIVER$$aconferenceObject 000873632 3367_ $$0PUB:(DE-HGF)3$$2PUB:(DE-HGF)$$aBook$$mbook 000873632 3367_ $$2DataCite$$aOutput Types/Conference Abstract 000873632 3367_ $$2ORCID$$aOTHER 000873632 520__ $$aSpiking Neural Networks (SNNs) are a promising computational paradigm, both to understand biological information processing and for low-power, embedded chips. Although SNNs are known to encode information in the precise timing of spikes, conventional artificial learning algorithms do not take this into account directly. In this work, we implement the spike timing by training the synaptic delays in a single layer SNN. We use two different approaches: a classical gradient descent and a direct algebraic method that is based on a complex-valued encoding of the spikes. Both algorithms are equally able to correctly solve simple detection tasks. Our work provides new optimization methods for the data analysis of highly time-dependent data and training methods for neuromorphic chips. 000873632 536__ $$0G:(DE-HGF)POF3-574$$a574 - Theory, modelling and simulation (POF3-574)$$cPOF3-574$$fPOF III$$x0 000873632 536__ $$0G:(EU-Grant)90251$$aSmartstart - SMARTSTART Training Program in Computational Neuroscience (90251)$$c90251$$x1 000873632 588__ $$aDataset connected to CrossRef Book Series 000873632 7001_ $$00000-0002-8181-2128$$aKůrková, Věra$$b1$$eEditor 000873632 7001_ $$00000-0003-4786-9806$$aKarpov, Pavel$$b2$$eEditor 000873632 7001_ $$00000-0002-2419-1943$$aTheis, Fabian$$b3$$eEditor 000873632 7001_ $$00000-0001-8084-5297$$aState, Laura$$b4 000873632 7001_ $$00000-0002-1218-4009$$aVilimelis Aceituno, Pau$$b5$$eCorresponding author 000873632 773__ $$a10.1007/978-3-030-30487-4_54 000873632 909CO $$ooai:juser.fz-juelich.de:873632$$pec_fundedresources$$pVDB$$popenaire 000873632 9101_ $$0I:(DE-588b)5008462-8$$60000-0001-8084-5297$$aForschungszentrum Jülich$$b4$$kFZJ 000873632 9131_ $$0G:(DE-HGF)POF3-574$$1G:(DE-HGF)POF3-570$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lDecoding the Human Brain$$vTheory, modelling and simulation$$x0 000873632 9141_ $$y2020 000873632 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz 000873632 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS 000873632 9201_ $$0I:(DE-Juel1)INM-6-20090406$$kINM-6$$lComputational and Systems Neuroscience$$x0 000873632 9201_ $$0I:(DE-Juel1)IAS-6-20130828$$kIAS-6$$lTheoretical Neuroscience$$x1 000873632 9201_ $$0I:(DE-Juel1)INM-10-20170113$$kINM-10$$lJara-Institut Brain structure-function relationships$$x2 000873632 980__ $$aabstract 000873632 980__ $$aVDB 000873632 980__ $$abook 000873632 980__ $$aI:(DE-Juel1)INM-6-20090406 000873632 980__ $$aI:(DE-Juel1)IAS-6-20130828 000873632 980__ $$aI:(DE-Juel1)INM-10-20170113 000873632 980__ $$aUNRESTRICTED 000873632 981__ $$aI:(DE-Juel1)IAS-6-20130828