An Efficient Multilayer Spiking Convolutional Neural Network Processor for Object Recognition With Low Bitwidth and Channel-Level Parallelism

Previous studies have shown that the event-driven multilayer spiking convolutional neural network (SCNN) can reduce computational complexity largely while keeping accurate. To fully utilize the advantages of SCNN, this brief proposed an efficient multilayer SCNN processor for object recognition. The...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on circuits and systems. II, Express briefs Ročník 69; číslo 12; s. 5129 - 5133
Hlavní autoři:	Feng, Lichen, Zhang, Yueqi, Zhu, Zhangming
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.12.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Artificial neural networks Channel-level parallel Convolutional neural networks Encoding Image classification Microprocessors Multilayers Neurons Nonhomogeneous media Object recognition Parallel operation Random access memory rank-order coding sparse event spike-centric Spiking spiking convolutional neural network Support vector machines
ISSN:	1549-7747, 1558-3791
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Previous studies have shown that the event-driven multilayer spiking convolutional neural network (SCNN) can reduce computational complexity largely while keeping accurate. To fully utilize the advantages of SCNN, this brief proposed an efficient multilayer SCNN processor for object recognition. The interconnection between spiking layers is implemented for the first time. The rank-order coding with mutual and lateral inhibitions enables sparse event transmission. By further combining the spike-centric membrane potential update, channel-level parallel operation, and the low bitwidths of synapse weights and potentials, the proposed design achieves 500 classifications/s, and 68 uJ/classification for recognizing images with <inline-formula> <tex-math notation="LaTeX">160\mathbf {\times }250 </tex-math></inline-formula> resolution, which is superior to the recent works.
AbstractList	Previous studies have shown that the event-driven multilayer spiking convolutional neural network (SCNN) can reduce computational complexity largely while keeping accurate. To fully utilize the advantages of SCNN, this brief proposed an efficient multilayer SCNN processor for object recognition. The interconnection between spiking layers is implemented for the first time. The rank-order coding with mutual and lateral inhibitions enables sparse event transmission. By further combining the spike-centric membrane potential update, channel-level parallel operation, and the low bitwidths of synapse weights and potentials, the proposed design achieves 500 classifications/s, and 68 uJ/classification for recognizing images with [Formula Omitted] resolution, which is superior to the recent works. Previous studies have shown that the event-driven multilayer spiking convolutional neural network (SCNN) can reduce computational complexity largely while keeping accurate. To fully utilize the advantages of SCNN, this brief proposed an efficient multilayer SCNN processor for object recognition. The interconnection between spiking layers is implemented for the first time. The rank-order coding with mutual and lateral inhibitions enables sparse event transmission. By further combining the spike-centric membrane potential update, channel-level parallel operation, and the low bitwidths of synapse weights and potentials, the proposed design achieves 500 classifications/s, and 68 uJ/classification for recognizing images with <inline-formula> <tex-math notation="LaTeX">160\mathbf {\times }250 </tex-math></inline-formula> resolution, which is superior to the recent works.
Author	Zhu, Zhangming Feng, Lichen Zhang, Yueqi
Author_xml	– sequence: 1 givenname: Lichen orcidid: 0000-0002-7685-2141 surname: Feng fullname: Feng, Lichen organization: Shaanxi Key Laboratory of Integrated Circuits and Systems, School of Microelectronics, Xidian University, Xi'an, China – sequence: 2 givenname: Yueqi surname: Zhang fullname: Zhang, Yueqi organization: Shaanxi Key Laboratory of Integrated Circuits and Systems, School of Microelectronics, Xidian University, Xi'an, China – sequence: 3 givenname: Zhangming orcidid: 0000-0002-7764-1928 surname: Zhu fullname: Zhu, Zhangming email: zmyh@263.net organization: Shaanxi Key Laboratory of Integrated Circuits and Systems, School of Microelectronics, Xidian University, Xi'an, China
BookMark	eNp9kE1P3DAQhi1EJT7aP1Auljhn649kHR8h4mOlbUFA1WPkOGPwYuzFdljxI_jPTVjUQw8cRjOjeZ9XmvcA7frgAaHvlMwoJfLHXXO7WMwYYWzGGRGyljton1ZVXXAh6e40l7IQohR76CClFSFMEs720duJx2fGWG3BZ_xzcNk69QoR367to_X3uAn-Jbgh2-CVw79giO8tb0J8xNcxaEgpRGzGuupWoDO-AR3uvZ0I_MfmB7wMG3xq88b246J8j5sH5T24Ygkv4PC1Gi0dOJuevqIvRrkE3z76Ifp9fnbXXBbLq4tFc7IsNJNVLnowptO0Mqoiikk1V52WJQHdMV5pAlTLbm56CUDrilNplADOypoJM-8k7fkhOt76rmN4HiDldhWGOD6YWibKivKypuWoqrcqHUNKEUyrbVbTXzkq61pK2in89j38dgq__Qh_RNl_6DraJxVfP4eOtpAFgH_AeJGCzPlfunGV4Q
CODEN	ITCSFK
CitedBy_id	crossref_primary_10_1109_TCSII_2023_3239039 crossref_primary_10_1109_TCSII_2025_3582265 crossref_primary_10_1109_TCSII_2024_3383655 crossref_primary_10_1109_TCSII_2024_3395415
Cites_doi	10.1109/JSSC.2007.914337 10.1016/j.neucom.2017.04.003 10.3389/fnins.2017.00123 10.1016/S0166-2236(96)80018-X 10.1016/j.neucom.2020.05.031 10.1109/JSSC.2018.2884901 10.1016/j.neucom.2018.11.014 10.1016/j.neucom.2016.09.071 10.1016/j.neunet.2017.12.005 10.55782/ane-2011-1862 10.1109/ISCAS.2010.5537907 10.3389/fnins.2017.00682 10.1109/IJCNN48605.2020.9207075 10.1109/TETCI.2019.2909936 10.3389/fncom.2015.00099
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION 7SP 8FD L7M
DOI	10.1109/TCSII.2022.3207989
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-3791
EndPage	5133
ExternalDocumentID	10_1109_TCSII_2022_3207989 9899706
Genre	orig-research
GrantInformation_xml	– fundername: Fundamental Research Funds for the Central Universities grantid: XJS211111 funderid: 10.13039/501100012226 – fundername: National Natural Science Foundation of China grantid: 62104175; 62021004 funderid: 10.13039/501100001809
GroupedDBID	0R~ 29I 4.4 5VS 6IK 6J9 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK AETIX AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD IFIPE IPLJI JAVBF M43 OCL PZZ RIA RIE RNS RXW TAE TAF VJK AAYXX CITATION 7SP 8FD L7M
ID	FETCH-LOGICAL-c295t-deffbc15fa50a29a6abc940ecb235c0e1c9b6fd9ee185319fa7e324827f6b91d3
IEDL.DBID	RIE
ISICitedReferencesCount	8
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000922028300101&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1549-7747
IngestDate	Mon Jun 30 06:26:50 EDT 2025 Sat Nov 29 02:23:22 EST 2025 Tue Nov 18 22:39:02 EST 2025 Wed Aug 27 02:29:15 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	12
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c295t-deffbc15fa50a29a6abc940ecb235c0e1c9b6fd9ee185319fa7e324827f6b91d3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-7764-1928 0000-0002-7685-2141
PQID	2745134814
PQPubID	85412
PageCount	5
ParticipantIDs	crossref_primary_10_1109_TCSII_2022_3207989 crossref_citationtrail_10_1109_TCSII_2022_3207989 proquest_journals_2745134814 ieee_primary_9899706
PublicationCentury	2000
PublicationDate	2022-12-01
PublicationDateYYYYMMDD	2022-12-01
PublicationDate_xml	– month: 12 year: 2022 text: 2022-12-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on circuits and systems. II, Express briefs
PublicationTitleAbbrev	TCSII
PublicationYear	2022
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref12 ref14 ref11 ref10 ponulak (ref6) 2011; 71 ref2 ref1 ref17 tapiador-morales (ref16) 2019; 13 ref19 ref18 ref8 ref7 ref9 ref5 yousefzadeh (ref15) 2015 horowitz (ref3) 2014 maass (ref4) 2002; 8
References_xml	– ident: ref19 doi: 10.1109/JSSC.2007.914337 – ident: ref10 doi: 10.1016/j.neucom.2017.04.003 – start-page: 1 year: 2015 ident: ref15 article-title: Fast pipeline 128?128pixel spiking convolution core for event-driven vision processing in FPGAs publication-title: Proc Int Conf Event Based Control Commun Signal Process (EBCCSP) – ident: ref5 doi: 10.3389/fnins.2017.00123 – ident: ref9 doi: 10.1016/S0166-2236(96)80018-X – ident: ref17 doi: 10.1016/j.neucom.2020.05.031 – ident: ref18 doi: 10.1109/JSSC.2018.2884901 – ident: ref8 doi: 10.1016/j.neucom.2018.11.014 – volume: 13 start-page: 159 year: 2019 ident: ref16 article-title: Neuromorphic LIF row-by-row multiconvolution processor for FPGA publication-title: IEEE Trans Biomed Circuits Syst – ident: ref14 doi: 10.1016/j.neucom.2016.09.071 – ident: ref13 doi: 10.1016/j.neunet.2017.12.005 – volume: 71 start-page: 409 year: 2011 ident: ref6 article-title: Introduction to spiking neural networks: Information processing, learning and applications publication-title: Acta Neurobiologiae Experimentali doi: 10.55782/ane-2011-1862 – ident: ref1 doi: 10.1109/ISCAS.2010.5537907 – ident: ref7 doi: 10.3389/fnins.2017.00682 – ident: ref11 doi: 10.1109/IJCNN48605.2020.9207075 – volume: 8 start-page: 32 year: 2002 ident: ref4 article-title: Computing with spikes publication-title: Found Inf Process TELEMATIK – start-page: 10 year: 2014 ident: ref3 article-title: Computing's energy problem (and what we can do about it) publication-title: IEEE Int Solid-State Circuits Conf Dig Tech Papers (ISSCC) – ident: ref2 doi: 10.1109/TETCI.2019.2909936 – ident: ref12 doi: 10.3389/fncom.2015.00099
SSID	ssj0029032
Score	2.3917186
Snippet	Previous studies have shown that the event-driven multilayer spiking convolutional neural network (SCNN) can reduce computational complexity largely while...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	5129
SubjectTerms	Artificial neural networks Channel-level parallel Convolutional neural networks Encoding Image classification Microprocessors Multilayers Neurons Nonhomogeneous media Object recognition Parallel operation Random access memory rank-order coding sparse event spike-centric Spiking spiking convolutional neural network Support vector machines
Title	An Efficient Multilayer Spiking Convolutional Neural Network Processor for Object Recognition With Low Bitwidth and Channel-Level Parallelism
URI	https://ieeexplore.ieee.org/document/9899706 https://www.proquest.com/docview/2745134814
Volume	69
WOSCitedRecordID	wos000922028300101&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-3791 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0029032 issn: 1549-7747 databaseCode: RIE dateStart: 20040101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEA4qHvTgW1xf5OBNq2l32-wcdVEUFhXft5JXsbC2slv1V_ifnUm7i6AIntpCEgJf0vkmmfmGsT1k4LFB4h0ooGtGbW2gQYUBThrJtnBZraX30JeXl92nJ7ieYgeTXBjnnA8-c4f06u_ybWne6KjsCNA5kKSvPS1lUudqTZwrEL4YGSmOIWPsyHGCjICju97txQW6glF02I6EBCrp_s0I-aoqP37F3r6cLf5vZktsoeGR_LgGfplNuWKFzX9TF1xln8cFP_UKEdiX-0zbgUKGzW9fczog572yeG9WHg5FMh3-4ePCeZNBUA450lp-pem8ht-Mw43Kgj_m1TPvlx_8JK8-cosfqrCcshUKNwj6FIzEr9WQarUM8tHLGrs_O73rnQdN9YXARBBXgXVZpk0YZyoWKgKVKG2gI5zRUTs2woUGdJJZcI5MfgiZkg7ZWTeSWaIhtO11NlOUhdtgHBIrpYi7OtQS3fEErEaLGelEOSQsst1i4RiO1DTS5FQhY5B6F0VA6iFMCcK0gbDF9id9Xmthjj9brxJok5YNXi22PUY9bfbuKEU_PQ4pP7mz-XuvLTZHY9dBLdtsphq-uR02a96rfDTc9cvyC8kg4jQ
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Nb9QwEB1VLRJwKB-lYksLPnCDtI43idfHsmrVFWGp6AK9Rf6KiLQk1W7a_or-Z2ac7KoSFRKnJJKdWHp25o098wbgPTLw1CLxjrSiY0bjXGSUjiMcNJJt7stOS-9HLqfT0eWlOt-Aj-tcGO99CD7zh3QbzvJdY69pq-xIoXMgSV97K00SwbtsrbV7pXgoR0aaY8gZE7lKkeHqaDa-mEzQGRTicCi4VFTU_Z4ZCnVV_voZBwtz-uz_xvYctnsmyY476F_Ahq9fwtN7-oI7cHdcs5OgEYF9Wci1nWvk2OziqqItcjZu6pt-7uGrSKgjXEJkOOtzCJoFQ2LLvhrasWHfVgFHTc1-Vu0vlje37FPV3lYOH3TtGOUr1H4e5RSOxM71gqq1zKvl71fw_fRkNj6L-voLkRUqbSPny9LYOC11yrVQOtPGqoR7a8QwtdzHVpmsdMp7MvqxKrX0yM9GQpaZUbEb7sJm3dT-NTCVOSl5OjKxkeiQZ8oZtJnCZNojZZHDAcQrOArbi5NTjYx5EZwUrooAYUEQFj2EA_iw7nPVSXP8s_UOgbZu2eM1gP0V6kW_epcFeuppTBnKyd7Dvd7B47PZl7zIJ9PPb-AJfacLcdmHzXZx7Q_gkb1pq-XibZiifwCvw-V7
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=An+Efficient+Multilayer+Spiking+Convolutional+Neural+Network+Processor+for+Object+Recognition+With+Low+Bitwidth+and+Channel-Level+Parallelism&rft.jtitle=IEEE+transactions+on+circuits+and+systems.+II%2C+Express+briefs&rft.au=Feng%2C+Lichen&rft.au=Zhang%2C+Yueqi&rft.au=Zhu%2C+Zhangming&rft.date=2022-12-01&rft.issn=1549-7747&rft.eissn=1558-3791&rft.volume=69&rft.issue=12&rft.spage=5129&rft.epage=5133&rft_id=info:doi/10.1109%2FTCSII.2022.3207989&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TCSII_2022_3207989
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1549-7747&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1549-7747&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1549-7747&client=summon