000873633 001__ 873633 000873633 005__ 20240313094942.0 000873633 0247_ $$2doi$$a10.1109/NER.2019.8716891 000873633 0247_ $$2WOS$$aWOS:000469933200299 000873633 037__ $$aFZJ-2020-00876 000873633 1001_ $$0P:(DE-Juel1)171331$$aHe, Xu$$b0$$ufzj 000873633 1112_ $$a2019 9th International IEEE/EMBS Conference on Neural Engineering (NER)$$cSan Francisco$$d2019-03-20 - 2019-03-23$$wCA 000873633 245__ $$aReservoir Transfer on Analog Neuromorphic Hardware 000873633 260__ $$c2019 000873633 3367_ $$0PUB:(DE-HGF)1$$2PUB:(DE-HGF)$$aAbstract$$babstract$$mabstract$$s1580903721_16416 000873633 3367_ $$033$$2EndNote$$aConference Paper 000873633 3367_ $$2BibTeX$$aINPROCEEDINGS 000873633 3367_ $$2DRIVER$$aconferenceObject 000873633 3367_ $$2DataCite$$aOutput Types/Conference Abstract 000873633 3367_ $$2ORCID$$aOTHER 000873633 500__ $$aTianlin Liu was supported by the FZJ through the project SMARTSTART Computational Neuroscience, DB001423. 000873633 520__ $$aAnalog, unclocked, spiking neuromorphic microchips open new perspectives for implantable or wearable biosensors and biocontrollers, due to their low energy consumption and heat dissipation. However, the challenges from a computational point of view are formidable. Here we outline our solutions to realize the reservoir computing paradigm on such hardware and address the combined problems of low bit resolution, device mismatch, approximate neuron models, and timescale mismatch. The main contribution is a computational scheme, called Reservoir Transfer, which enables us to transfer the dynamical properties of a well-performing neural network which has been optimized on a digital computer, onto neuromorphic hardware that displays the abovementioned problematic properties. Here we present a case study of implementing an ECG heartbeat abnormality detector to showcase the proposed method. 000873633 536__ $$0G:(DE-HGF)POF3-574$$a574 - Theory, modelling and simulation (POF3-574)$$cPOF3-574$$fPOF III$$x0 000873633 536__ $$0G:(EU-Grant)90251$$aSmartstart - SMARTSTART Training Program in Computational Neuroscience (90251)$$c90251$$x1 000873633 588__ $$aDataset connected to CrossRef Conference 000873633 7001_ $$0P:(DE-HGF)0$$aLiu, Tianlin$$b1 000873633 7001_ $$0P:(DE-HGF)0$$aHadaeghi, Fatemeh$$b2 000873633 7001_ $$0P:(DE-HGF)0$$aJaeger, Herbert$$b3 000873633 773__ $$a10.1109/NER.2019.8716891 000873633 909CO $$ooai:juser.fz-juelich.de:873633$$pec_fundedresources$$pVDB$$popenaire 000873633 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171331$$aForschungszentrum Jülich$$b0$$kFZJ 000873633 9131_ $$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$$x0 000873633 9141_ $$y2019 000873633 9201_ $$0I:(DE-Juel1)INM-6-20090406$$kINM-6$$lComputational and Systems Neuroscience$$x0 000873633 9201_ $$0I:(DE-Juel1)INM-10-20170113$$kINM-10$$lJara-Institut Brain structure-function relationships$$x1 000873633 9201_ $$0I:(DE-Juel1)IAS-6-20130828$$kIAS-6$$lTheoretical Neuroscience$$x2 000873633 980__ $$aabstract 000873633 980__ $$aVDB 000873633 980__ $$aI:(DE-Juel1)INM-6-20090406 000873633 980__ $$aI:(DE-Juel1)INM-10-20170113 000873633 980__ $$aI:(DE-Juel1)IAS-6-20130828 000873633 980__ $$aUNRESTRICTED 000873633 981__ $$aI:(DE-Juel1)IAS-6-20130828