000893059 001__ 893059
000893059 005__ 20220126143614.0
000893059 0247_ $$2doi$$a10.3389/fnins.2021.661856
000893059 0247_ $$2ISSN$$a1662-453X
000893059 0247_ $$2ISSN$$a1662-4548
000893059 0247_ $$2Handle$$a2128/27910
000893059 0247_ $$2altmetric$$aaltmetric:107929836
000893059 0247_ $$2pmid$$a34163323
000893059 0247_ $$2WOS$$aWOS:000663741500001
000893059 037__ $$aFZJ-2021-02533
000893059 082__ $$a610
000893059 1001_ $$0P:(DE-Juel1)188159$$aBengel, Christopher$$b0
000893059 245__ $$aUtilizing the Switching Stochasticity of HfO2/TiOx-Based ReRAM Devices and the Concept of Multiple Device Synapses for the Classification of Overlapping and Noisy Patterns
000893059 260__ $$aLausanne$$bFrontiers Research Foundation$$c2021
000893059 3367_ $$2DRIVER$$aarticle
000893059 3367_ $$2DataCite$$aOutput Types/Journal article
000893059 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1643200548_11108
000893059 3367_ $$2BibTeX$$aARTICLE
000893059 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000893059 3367_ $$00$$2EndNote$$aJournal Article
000893059 520__ $$aWith the arrival of the Internet of Things (IoT) and the challenges arising from Big Data, neuromorphic chip concepts are seen as key solutions for coping with the massive amount of unstructured data streams by moving the computation closer to the sensors, the so-called “edge computing.” Augmenting these chips with emerging memory technologies enables these edge devices with non-volatile and adaptive properties which are desirable for low power and online learning operations. However, an energy- and area-efficient realization of these systems requires disruptive hardware changes. Memristor-based solutions for these concepts are in the focus of research and industry due to their low-power and high-density online learning potential. Specifically, the filamentary-type valence change mechanism (VCM memories) have shown to be a promising candidate In consequence, physical models capturing a broad spectrum of experimentally observed features such as the pronounced cycle-to-cycle (c2c) and device-to-device (d2d) variability are required for accurate evaluation of the proposed concepts. In this study, we present an in-depth experimental analysis of d2d and c2c variability of filamentary-type bipolar switching HfO2/TiOx nano-sized crossbar devices and match the experimentally observed variabilities to our physically motivated JART VCM compact model. Based on this approach, we evaluate the concept of parallel operation of devices as a synapse both experimentally and theoretically. These parallel synapses form a synaptic array which is at the core of neuromorphic chips. We exploit the c2c variability of these devices for stochastic online learning which has shown to increase the effective bit precision of the devices. Finally, we demonstrate that stochastic switching features for a pattern classification task that can be employed in an online learning neural network.
000893059 536__ $$0G:(DE-HGF)POF4-523$$a523 - Neuromorphic Computing and Network Dynamics (POF4-523)$$cPOF4-523$$fPOF IV$$x0
000893059 536__ $$0G:(DE-HGF)POF4-5233$$a5233 - Memristive Materials and Devices (POF4-523)$$cPOF4-523$$fPOF IV$$x1
000893059 536__ $$0G:(DE-Juel1)aca_20190115$$aAdvanced Computing Architectures (aca_20190115)$$caca_20190115$$fAdvanced Computing Architectures$$x2
000893059 536__ $$0G:(EU-Grant)780215$$aMNEMOSENE - Computation-in-memory architecture based on resistive devices (780215)$$c780215$$fH2020-ICT-2017-1$$x3
000893059 536__ $$0G:(BMBF)16ES1133K$$aVerbundprojekt: Neuro-inspirierte Technologien der künstlichen Intelligenz für die Elektronik der Zukunft - NEUROTEC -, Teilvorhaben: Forschungszentrum Jülich (16ES1133K)$$c16ES1133K$$x4
000893059 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
000893059 7001_ $$0P:(DE-Juel1)173924$$aCüppers, Felix$$b1
000893059 7001_ $$0P:(DE-HGF)0$$aPayvand, Melika$$b2
000893059 7001_ $$0P:(DE-Juel1)130620$$aDittmann, Regina$$b3
000893059 7001_ $$0P:(DE-Juel1)131022$$aWaser, R.$$b4
000893059 7001_ $$0P:(DE-Juel1)130717$$aHoffmann-Eifert, Susanne$$b5$$ufzj
000893059 7001_ $$0P:(DE-Juel1)158062$$aMenzel, Stephan$$b6$$eCorresponding author
000893059 773__ $$0PERI:(DE-600)2411902-7$$a10.3389/fnins.2021.661856$$gVol. 15, p. 661856$$p661856$$tFrontiers in neuroscience$$v15$$x1662-453X$$y2021
000893059 8564_ $$uhttps://juser.fz-juelich.de/record/893059/files/fnins-15-661856.pdf$$yOpenAccess
000893059 909CO $$ooai:juser.fz-juelich.de:893059$$pVDB$$pdriver$$popen_access$$popenaire$$pec_fundedresources$$pdnbdelivery
000893059 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188159$$aForschungszentrum Jülich$$b0$$kFZJ
000893059 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)173924$$aForschungszentrum Jülich$$b1$$kFZJ
000893059 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)130620$$aForschungszentrum Jülich$$b3$$kFZJ
000893059 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131022$$aForschungszentrum Jülich$$b4$$kFZJ
000893059 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)130717$$aForschungszentrum Jülich$$b5$$kFZJ
000893059 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)158062$$aForschungszentrum Jülich$$b6$$kFZJ
000893059 9131_ $$0G:(DE-HGF)POF4-523$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x0
000893059 9131_ $$0G:(DE-HGF)POF4-523$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5233$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x1
000893059 9130_ $$0G:(DE-HGF)POF3-521$$1G:(DE-HGF)POF3-520$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lFuture Information Technology - Fundamentals, Novel Concepts and Energy Efficiency (FIT)$$vControlling Electron Charge-Based Phenomena$$x0
000893059 9141_ $$y2021
000893059 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2021-05-04
000893059 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2021-05-04
000893059 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2021-05-04
000893059 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2021-05-04
000893059 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000893059 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000893059 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bFRONT NEUROSCI-SWITZ : 2019$$d2021-05-04
000893059 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2021-05-04
000893059 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2021-05-04
000893059 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine$$d2021-05-04
000893059 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2021-05-04
000893059 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2021-05-04
000893059 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2021-05-04
000893059 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2021-05-04
000893059 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Blind peer review$$d2021-05-04
000893059 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2021-05-04
000893059 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2021-05-04
000893059 915__ $$0StatID:(DE-HGF)0320$$2StatID$$aDBCoverage$$bPubMed Central$$d2021-05-04
000893059 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2021-05-04
000893059 9201_ $$0I:(DE-Juel1)PGI-7-20110106$$kPGI-7$$lElektronische Materialien$$x0
000893059 9201_ $$0I:(DE-82)080009_20140620$$kJARA-FIT$$lJARA-FIT$$x1
000893059 9201_ $$0I:(DE-Juel1)PGI-10-20170113$$kPGI-10$$lJARA Institut Green IT$$x2
000893059 980__ $$ajournal
000893059 980__ $$aVDB
000893059 980__ $$aI:(DE-Juel1)PGI-7-20110106
000893059 980__ $$aI:(DE-82)080009_20140620
000893059 980__ $$aI:(DE-Juel1)PGI-10-20170113
000893059 980__ $$aUNRESTRICTED
000893059 9801_ $$aFullTexts