000904613 001__ 904613
000904613 005__ 20230123101913.0
000904613 0247_ $$2doi$$a10.1038/s41467-021-25873-0
000904613 0247_ $$2Handle$$a2128/31517
000904613 0247_ $$2altmetric$$aaltmetric:101740839
000904613 0247_ $$2pmid$$apmid:34608133
000904613 0247_ $$2WOS$$aWOS:000703617100028
000904613 037__ $$aFZJ-2021-06183
000904613 082__ $$a500
000904613 1001_ $$00000-0002-4501-8672$$aPedretti, Giacomo$$b0
000904613 245__ $$aTree-based machine learning performed in-memory with memristive analog CAM
000904613 260__ $$a[London]$$bNature Publishing Group UK$$c2021
000904613 3367_ $$2DRIVER$$aarticle
000904613 3367_ $$2DataCite$$aOutput Types/Journal article
000904613 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1658488715_6966
000904613 3367_ $$2BibTeX$$aARTICLE
000904613 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000904613 3367_ $$00$$2EndNote$$aJournal Article
000904613 520__ $$aTree-based machine learning techniques, such as Decision Trees and Random Forests, are top performers in several domains as they do well with limited training datasets and offer improved interpretability compared to Deep Neural Networks (DNN). However, these models are difficult to optimize for fast inference at scale without accuracy loss in von Neumann architectures due to non-uniform memory access patterns. Recently, we proposed a novel analog content addressable memory (CAM) based on emerging memristor devices for fast look-up table operations. Here, we propose for the first time to use the analog CAM as an in-memory computational primitive to accelerate tree-based model inference. We demonstrate an efficient mapping algorithm leveraging the new analog CAM capabilities such that each root to leaf path of a Decision Tree is programmed into a row. This new in-memory compute concept for enables few-cycle model inference, dramatically increasing 103 × the throughput over conventional approaches.
000904613 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x0
000904613 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
000904613 7001_ $$00000-0002-0907-583X$$aGraves, Catherine E.$$b1
000904613 7001_ $$0P:(DE-HGF)0$$aSerebryakov, Sergey$$b2
000904613 7001_ $$0P:(DE-HGF)0$$aMao, Ruibin$$b3
000904613 7001_ $$0P:(DE-HGF)0$$aSheng, Xia$$b4
000904613 7001_ $$0P:(DE-HGF)0$$aFoltin, Martin$$b5
000904613 7001_ $$00000-0003-3795-2008$$aLi, Can$$b6
000904613 7001_ $$0P:(DE-Juel1)188145$$aStrachan, John Paul$$b7$$eCorresponding author$$ufzj
000904613 773__ $$0PERI:(DE-600)2553671-0$$a10.1038/s41467-021-25873-0$$gVol. 12, no. 1, p. 5806$$n1$$p5806$$tNature Communications$$v12$$x2041-1723$$y2021
000904613 8564_ $$uhttps://juser.fz-juelich.de/record/904613/files/s41467-021-25873-0.pdf$$yOpenAccess
000904613 909CO $$ooai:juser.fz-juelich.de:904613$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000904613 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188145$$aForschungszentrum Jülich$$b7$$kFZJ
000904613 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$$x0
000904613 9141_ $$y2022
000904613 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)1040$$2StatID$$aDBCoverage$$bZoological Record$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)1060$$2StatID$$aDBCoverage$$bCurrent Contents - Agriculture, Biology and Environmental Sciences$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bNAT COMMUN : 2019$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000904613 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2021-02-02
000904613 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000904613 915__ $$0StatID:(DE-HGF)9910$$2StatID$$aIF >= 10$$bNAT COMMUN : 2019$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Peer review$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2021-02-02
000904613 915__ $$0StatID:(DE-HGF)0320$$2StatID$$aDBCoverage$$bPubMed Central$$d2021-02-02
000904613 9201_ $$0I:(DE-Juel1)PGI-14-20210412$$kPGI-14$$lNeuromorphic Compute Nodes$$x0
000904613 9801_ $$aFullTexts
000904613 980__ $$ajournal
000904613 980__ $$aVDB
000904613 980__ $$aUNRESTRICTED
000904613 980__ $$aI:(DE-Juel1)PGI-14-20210412