001032331 001__ 1032331
001032331 005__ 20250203133217.0
001032331 0247_ $$2doi$$a10.1038/s41467-024-53827-9
001032331 0247_ $$2datacite_doi$$a10.34734/FZJ-2024-06157
001032331 0247_ $$2pmid$$a39516210
001032331 0247_ $$2WOS$$aWOS:001352395400002
001032331 037__ $$aFZJ-2024-06157
001032331 082__ $$a500
001032331 1001_ $$0P:(DE-Juel1)201426$$aRenner, Alpha$$b0$$eFirst author$$ufzj
001032331 245__ $$aThe backpropagation algorithm implemented on spiking neuromorphic hardware
001032331 260__ $$a[London]$$bNature Publishing Group UK$$c2024
001032331 3367_ $$2DRIVER$$aarticle
001032331 3367_ $$2DataCite$$aOutput Types/Journal article
001032331 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1734427622_29623
001032331 3367_ $$2BibTeX$$aARTICLE
001032331 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001032331 3367_ $$00$$2EndNote$$aJournal Article
001032331 520__ $$aThe capabilities of natural neural systems have inspired both new generations of machine learning algorithms as well as neuromorphic, very large-scale integrated circuits capable of fast, low-power information processing. However, it has been argued that most modern machine learning algorithms are not neurophysiologically plausible. In particular, the workhorse of modern deep learning, the backpropagation algorithm, has proven difficult to translate to neuromorphic hardware. This study presents a neuromorphic, spiking backpropagation algorithm based on synfire-gated dynamical information coordination and processing implemented on Intel’s Loihi neuromorphic research processor. We demonstrate a proof-of-principle three-layer circuit that learns to classify digits and clothing items from the MNIST and Fashion MNIST datasets. To our knowledge, this is the first work to show a Spiking Neural Network implementation of the exact backpropagation algorithm that is fully on-chip without a computer in the loop. It is competitive in accuracy with off-chip trained SNNs and achieves an energy-delay product suitable for edge computing. This implementation shows a path for using in-memory, massively parallel neuromorphic processors for low-power, low-latency implementation of modern deep learning applications.
001032331 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001032331 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001032331 7001_ $$0P:(DE-HGF)0$$aSheldon, Forrest$$b1
001032331 7001_ $$0P:(DE-HGF)0$$aZlotnik, Anatoly$$b2
001032331 7001_ $$0P:(DE-HGF)0$$aTao, Louis$$b3
001032331 7001_ $$0P:(DE-HGF)0$$aSornborger, Andrew$$b4$$eCorresponding author
001032331 773__ $$0PERI:(DE-600)2553671-0$$a10.1038/s41467-024-53827-9$$gVol. 15, no. 1, p. 9691$$n1$$p9691$$tNature Communications$$v15$$x2041-1723$$y2024
001032331 8564_ $$uhttps://juser.fz-juelich.de/record/1032331/files/s41467-024-53827-9.pdf$$yOpenAccess
001032331 909CO $$ooai:juser.fz-juelich.de:1032331$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
001032331 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)201426$$aForschungszentrum Jülich$$b0$$kFZJ
001032331 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)POF4-5234$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x0
001032331 9141_ $$y2024
001032331 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2023-08-29
001032331 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2023-08-29
001032331 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2023-08-29
001032331 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001032331 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2023-08-29
001032331 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001032331 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2023-08-29
001032331 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bNAT COMMUN : 2022$$d2025-01-02
001032331 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2025-01-02
001032331 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2025-01-02
001032331 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-01-30T07:48:07Z
001032331 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-01-30T07:48:07Z
001032331 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Peer review$$d2024-01-30T07:48:07Z
001032331 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2025-01-02
001032331 915__ $$0StatID:(DE-HGF)1040$$2StatID$$aDBCoverage$$bZoological Record$$d2025-01-02
001032331 915__ $$0StatID:(DE-HGF)1060$$2StatID$$aDBCoverage$$bCurrent Contents - Agriculture, Biology and Environmental Sciences$$d2025-01-02
001032331 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2025-01-02
001032331 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2025-01-02
001032331 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences$$d2025-01-02
001032331 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2025-01-02
001032331 915__ $$0StatID:(DE-HGF)9915$$2StatID$$aIF >= 15$$bNAT COMMUN : 2022$$d2025-01-02
001032331 9201_ $$0I:(DE-Juel1)PGI-15-20210701$$kPGI-15$$lNeuromorphic Software Eco System$$x0
001032331 980__ $$ajournal
001032331 980__ $$aVDB
001032331 980__ $$aUNRESTRICTED
001032331 980__ $$aI:(DE-Juel1)PGI-15-20210701
001032331 9801_ $$aFullTexts