Gradual Surrogate Gradient Learning in Deep Spiking Neural Networks

Spiking Neural Network (SNN) is a promising solution for ultra-low-power hardware. Recent SNNs have reached the performance of Deep Neural Networks (DNNs) in dealing with many tasks. However, these methods often suffer from a long simulation time to achieve the accurate spike train information. In a...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 8927 - 8931
Main Authors: Chen, Yi, Zhang, Silin, Ren, Shiyu, Qu, Hong
Format: Conference Proceeding
Language:English
Published: IEEE 23.05.2022
Subjects:
ISSN:2379-190X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Spiking Neural Network (SNN) is a promising solution for ultra-low-power hardware. Recent SNNs have reached the performance of Deep Neural Networks (DNNs) in dealing with many tasks. However, these methods often suffer from a long simulation time to achieve the accurate spike train information. In addition, these methods are contingent on a well-designed initialization to effectively transmit the gradient information. To address these issues, we propose the Internal Spiking Neuron Model (ISNM), which uses the synaptic current instead of spike trains as the carrier of information. In addition, we design a gradual surrogate gradient learning algorithm to ensure that SNNs effectively back-propagate gradient information in the early stage of training and more accurate gradient information in the later stage of training. The experiments on various network structures on CIFAR-10 and CIFAR-100 datasets show that the proposed method can exceed the performance of previous SNN methods within 5 time steps.
AbstractList Spiking Neural Network (SNN) is a promising solution for ultra-low-power hardware. Recent SNNs have reached the performance of Deep Neural Networks (DNNs) in dealing with many tasks. However, these methods often suffer from a long simulation time to achieve the accurate spike train information. In addition, these methods are contingent on a well-designed initialization to effectively transmit the gradient information. To address these issues, we propose the Internal Spiking Neuron Model (ISNM), which uses the synaptic current instead of spike trains as the carrier of information. In addition, we design a gradual surrogate gradient learning algorithm to ensure that SNNs effectively back-propagate gradient information in the early stage of training and more accurate gradient information in the later stage of training. The experiments on various network structures on CIFAR-10 and CIFAR-100 datasets show that the proposed method can exceed the performance of previous SNN methods within 5 time steps.
Author Chen, Yi
Zhang, Silin
Qu, Hong
Ren, Shiyu
Author_xml – sequence: 1
  givenname: Yi
  surname: Chen
  fullname: Chen, Yi
  organization: University of Electronic Science and Technology of China,School of Computer Science and Engineering,China
– sequence: 2
  givenname: Silin
  surname: Zhang
  fullname: Zhang, Silin
  organization: University of Electronic Science and Technology of China,School of Computer Science and Engineering,China
– sequence: 3
  givenname: Shiyu
  surname: Ren
  fullname: Ren, Shiyu
  organization: University of Electronic Science and Technology of China,School of Computer Science and Engineering,China
– sequence: 4
  givenname: Hong
  surname: Qu
  fullname: Qu, Hong
  email: hongqu@uestc.edu.cn
  organization: University of Electronic Science and Technology of China,School of Computer Science and Engineering,China
BookMark eNotT11LxDAQjKLg9fQX-JI_0HObpPl4lKqnUE6hCr4dSbs94p1tSVvEf28OD5ZdZphZZhJy0fUdEkIzWGUZmLuX4r6q3gQ3jK0YxGWUkEqJM5JkUuYC4shzsmBcmTQz8HlFknH8AgCthF6QYh1sM9sDreYQ-p2dkB4Zj91ES7Sh892O-o4-IA60Gvz-iDc4h2jZ4PTTh_14TS5bexjx5nSX5OPp8b14TsvXdcxXpp4Bn1LOmrrV6IxxVqDLa2m00roGlTuBUpgcnMljKq4aF2uA1aqNYkAnWaMYX5Lb_78eEbdD8N82_G5PhfkfzK9NAw
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICASSP43922.2022.9746774
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 1665405406
9781665405409
EISSN 2379-190X
EndPage 8931
ExternalDocumentID 9746774
Genre orig-research
GrantInformation_xml – fundername: China Postdoctoral Science Foundation
  funderid: 10.13039/501100002858
– fundername: National Science Foundation
  funderid: 10.13039/100000001
GroupedDBID 23M
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
IPLJI
M43
OCL
RIE
RIL
RIO
RNS
ID FETCH-LOGICAL-i203t-32dcf8eb99ba4eb5c698788c075b4e64950b9574837db9740a87f99b0eb62d723
IEDL.DBID RIE
ISICitedReferencesCount 10
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000864187909048&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:25:03 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-32dcf8eb99ba4eb5c698788c075b4e64950b9574837db9740a87f99b0eb62d723
PageCount 5
ParticipantIDs ieee_primary_9746774
PublicationCentury 2000
PublicationDate 2022-May-23
PublicationDateYYYYMMDD 2022-05-23
PublicationDate_xml – month: 05
  year: 2022
  text: 2022-May-23
  day: 23
PublicationDecade 2020
PublicationTitle Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998)
PublicationTitleAbbrev ICASSP
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0008748
Score 2.3183744
Snippet Spiking Neural Network (SNN) is a promising solution for ultra-low-power hardware. Recent SNNs have reached the performance of Deep Neural Networks (DNNs) in...
SourceID ieee
SourceType Publisher
StartPage 8927
SubjectTerms Deep learning
Hardware
Learning systems
Neurons
Signal processing
Signal processing algorithms
Spiking Neural Networks
Spiking Neuron Model
Surrogate Gradient
Training
Title Gradual Surrogate Gradient Learning in Deep Spiking Neural Networks
URI https://ieeexplore.ieee.org/document/9746774
WOSCitedRecordID wos000864187909048&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5q8aAXH634JgePrl03aR5HqVYFKYVV6K3sJFPZy7ZsW3-_ye5aFbx4CSEkJExIJpmZ7xuAK0ShOFe3kX8r8MifRBWhchg5qXGmtORYk7i-qNFITyZm3ILrDRaGiKrgM7oJ1cqX7-Z2HUxlPRNyYyixBVtKyRqrtbl1tRL6K1InNr3nwV2ajr22TQLayhfN2F9JVCodMtz73-z70P0G47HxRs0cQIuKQ9j9wSPYgcFjmQVMFUvXZTkPhjEWWgLUkTUEqu8sL9g90YKlizyYx1mg5fBDRnUc-LILb8OH18FT1GRHiPIk5quIJ87ONKExmAnCvpVG-_-s9W8AFCT9xydG01eBMd6hX3ucaTXznWPy4ncq4UfQLuYFHQNDm2mUsc3QkXAuMU5I189QklVCuOwEOkEc00VNgDFtJHH6d_MZ7ASJBxd7ws-hvSrXdAHb9mOVL8vLatc-AS6kmSQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NT8MgFH-Z00S9-DGN33LwaF0ttMDRTOcWZ7OkM9lt6QNmeumWbvPvF9o6NfHihRACgTwCD957v98DuEFknFJ-79m3AvXsSeQeco2ejgROuYgoViSuAx7HYjyWwwbcrrEwxpgy-MzcuWrpy9cztXKmsrZ0uTE424DNkLHAr9Ba63tXcCa-YnV82e53HpJkaPVt4PBWtqhH_0qjUmqR7t7_5t-Ho284HhmuFc0BNEx-CLs_mARb0HkuUoeqIsmqKGbONEZciwM7kppC9Z1kOXk0Zk6SeeYM5MQRc9ghcRUJvjiCt-7TqNPz6vwIXhb4dOnRQKupMCglpsxgqCIp7I9W2VcAMhPZr4-PMuSOM16jXbufCj61nX1jN0DzgB5DM5_l5gQIqlRg5KsUtWFaB1KzSIcpRkZxxnR6Ci0njsm8osCY1JI4-7v5GrZ7o9fBZNCPX85hx0nfOdwDegHNZbEyl7ClPpbZorgqd_ATVSScaw
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=proceeding&rft.title=Proceedings+of+the+...+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+%281998%29&rft.atitle=Gradual+Surrogate+Gradient+Learning+in+Deep+Spiking+Neural+Networks&rft.au=Chen%2C+Yi&rft.au=Zhang%2C+Silin&rft.au=Ren%2C+Shiyu&rft.au=Qu%2C+Hong&rft.date=2022-05-23&rft.pub=IEEE&rft.eissn=2379-190X&rft.spage=8927&rft.epage=8931&rft_id=info:doi/10.1109%2FICASSP43922.2022.9746774&rft.externalDocID=9746774