000909568 001__ 909568
000909568 005__ 20230310131318.0
000909568 0247_ $$2doi$$a10.1002/aelm.202200448
000909568 0247_ $$2Handle$$a2128/32064
000909568 0247_ $$2WOS$$aWOS:000822534500001
000909568 037__ $$aFZJ-2022-03250
000909568 082__ $$a621.3
000909568 1001_ $$00000-0001-5385-3486$$aStecconi, Tommaso$$b0$$eCorresponding author
000909568 245__ $$aFilamentary TaO x /HfO 2 ReRAM Devices for Neural Networks Training with Analog In‐Memory Computing
000909568 260__ $$aWeinheim$$bWiley-VCH Verlag GmbH & Co. KG$$c2022
000909568 3367_ $$2DRIVER$$aarticle
000909568 3367_ $$2DataCite$$aOutput Types/Journal article
000909568 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1666081703_30577
000909568 3367_ $$2BibTeX$$aARTICLE
000909568 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000909568 3367_ $$00$$2EndNote$$aJournal Article
000909568 520__ $$aThe in-memory computing paradigm aims at overcoming the intrinsic inefficiencies of Von-Neumann computers by reducing the data-transport per arithmetic operation. Crossbar arrays of multilevel memristive devices enable efficient calculations of matrix-vector-multiplications, an operation extensively called on in artificial intelligence (AI) tasks. Resistive random-access memories (ReRAMs) are promising candidate devices for such applications. However, they generally exhibit large stochasticity and device-to-device variability. The integration of a sub-stoichiometric metal-oxide within the ReRAM stack can improve the resistive switching graduality and stochasticity. To this purpose, a conductive TaOx layer is developed and stacked on HfO2 between TiN electrodes, to create a complementary metal-oxide-semiconductor-compatible ReRAM structure. This device shows accumulative conductance updates in both directions, as required for training neural networks. Moreover, by reducing the TaOx thickness and by increasing its resistivity, the device resistive states increase, as required for reduced power consumption. An electric field-driven TaOx oxidation/reduction is responsible for the ReRAM switching. To demonstrate the potential of the optimized TaOx/HfO2 devices, the training of a fully-connected neural network on the Modified National Institute of Standards and Technology database dataset is simulated and benchmarked against a full precision digital implementation.
000909568 536__ $$0G:(DE-HGF)POF4-5233$$a5233 - Memristive Materials and Devices (POF4-523)$$cPOF4-523$$fPOF IV$$x0
000909568 536__ $$0G:(EU-Grant)861153$$aMANIC - Materials for Neuromorphic Circuits (861153)$$c861153$$fH2020-MSCA-ITN-2019$$x1
000909568 536__ $$0G:(GEPRIS)167917811$$aDFG project 167917811 - SFB 917: Resistiv schaltende Chalkogenide für zukünftige Elektronikanwendungen: Struktur, Kinetik und Bauelementskalierung "Nanoswitches" (167917811)$$c167917811$$x2
000909568 536__ $$0G:(DE-82)BMBF-16ME0398K$$aBMBF-16ME0398K - Verbundprojekt: Neuro-inspirierte Technologien der künstlichen Intelligenz für die Elektronik der Zukunft - NEUROTEC II - (BMBF-16ME0398K)$$cBMBF-16ME0398K$$x3
000909568 536__ $$0G:(DE-82)BMBF-16ME0404$$aBMBF-16ME0404 - Verbundprojekt: Neuro-inspirierte Technologien der künstlichen Intelligenz für die Elektronik der Zukunft - NEUROTEC II - (BMBF-16ME0404)$$cBMBF-16ME0404$$x4
000909568 536__ $$0G:(DE-Juel1)BMBF-03ZU1106AB$$aBMBF-03ZU1106AB - NeuroSys: "Memristor Crossbar Architekturen (Projekt A) - B" (BMBF-03ZU1106AB)$$cBMBF-03ZU1106AB$$x5
000909568 536__ $$0G:(DE-HGF)SO-092$$aACA - Advanced Computing Architectures (SO-092)$$cSO-092$$x6
000909568 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
000909568 7001_ $$0P:(DE-HGF)0$$aGuido, Roberto$$b1
000909568 7001_ $$0P:(DE-HGF)0$$aBerchialla, Luca$$b2
000909568 7001_ $$0P:(DE-HGF)0$$aLa Porta, Antonio$$b3
000909568 7001_ $$0P:(DE-HGF)0$$aWeiss, Jonas$$b4
000909568 7001_ $$0P:(DE-HGF)0$$aPopoff, Youri$$b5
000909568 7001_ $$0P:(DE-HGF)0$$aHalter, Mattia$$b6
000909568 7001_ $$0P:(DE-HGF)0$$aSousa, Marilyne$$b7
000909568 7001_ $$0P:(DE-HGF)0$$aHorst, Folkert$$b8
000909568 7001_ $$0P:(DE-HGF)0$$aDávila, Diana$$b9
000909568 7001_ $$0P:(DE-HGF)0$$aDrechsler, Ute$$b10
000909568 7001_ $$0P:(DE-Juel1)130620$$aDittmann, Regina$$b11
000909568 7001_ $$0P:(DE-HGF)0$$aOffrein, Bert Jan$$b12
000909568 7001_ $$0P:(DE-HGF)0$$aBragaglia, Valeria$$b13
000909568 773__ $$0PERI:(DE-600)2810904-1$$a10.1002/aelm.202200448$$gp. 2200448 -$$n10$$p2200448 -$$tAdvanced electronic materials$$v8$$x2199-160X$$y2022
000909568 8564_ $$uhttps://juser.fz-juelich.de/record/909568/files/Adv%20Elect%20Materials%20-%202022%20-%20Stecconi%20-%20Filamentary%20TaOx%20HfO2%20ReRAM%20Devices%20for%20Neural%20Networks%20Training%20with%20Analog.pdf$$yOpenAccess
000909568 909CO $$ooai:juser.fz-juelich.de:909568$$pdnbdelivery$$pec_fundedresources$$pVDB$$pdriver$$popen_access$$popenaire
000909568 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)130620$$aForschungszentrum Jülich$$b11$$kFZJ
000909568 9131_ $$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$$vNeuromorphic Computing and Network Dynamics$$x0
000909568 9141_ $$y2022
000909568 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000909568 915__ $$0StatID:(DE-HGF)3001$$2StatID$$aDEAL Wiley$$d2021-01-28$$wger
000909568 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2021-01-28
000909568 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000909568 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2021-01-28
000909568 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bADV ELECTRON MATER : 2021$$d2022-11-12
000909568 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2022-11-12
000909568 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2022-11-12
000909568 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2022-11-12
000909568 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2022-11-12
000909568 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2022-11-12
000909568 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bADV ELECTRON MATER : 2021$$d2022-11-12
000909568 9201_ $$0I:(DE-Juel1)PGI-7-20110106$$kPGI-7$$lElektronische Materialien$$x0
000909568 9201_ $$0I:(DE-82)080009_20140620$$kJARA-FIT$$lJARA-FIT$$x1
000909568 980__ $$ajournal
000909568 980__ $$aVDB
000909568 980__ $$aUNRESTRICTED
000909568 980__ $$aI:(DE-Juel1)PGI-7-20110106
000909568 980__ $$aI:(DE-82)080009_20140620
000909568 9801_ $$aFullTexts