SNNVis: Visualizing Graph Embedding of Evolutionary Optimization for Spiking Neural Networks

While Spiking Neural Networks (SNNs) show a lot of promise, it is difficult to optimize them because applying traditional gradient-based optimization techniques is difficult. Even though evolutionary algorithms (EAs) have been shown to promise to optimize SNNs, understanding the relationship between...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2024 International Conference on Neuromorphic Systems (ICONS) S. 327 - 330
Hauptverfasser: Chae, Junghoon, Lim, Seung-Hwan, Kulkarni, Shruti, Schuman, Catherine
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 30.07.2024
Schlagworte:
evolutionary algorithm
Evolutionary computation
Neuromorphics
Optimization
SNN
Spiking neural networks
Visual analytics
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract While Spiking Neural Networks (SNNs) show a lot of promise, it is difficult to optimize them because applying traditional gradient-based optimization techniques is difficult. Even though evolutionary algorithms (EAs) have been shown to promise to optimize SNNs, understanding the relationship between evolving the characteristics of SNNs and their performance to improve the optimization algorithm is challenging because of the complex characteristics and huge population size. We propose visual analytics with novel graph embedding for evolutionary SNNs to address the challenges. While existing graph embedding techniques have limitations in preserving the specific features of the nodes and edges, our approach maintains them. Also, we develop visual analytics for understanding the relationship between the network performance and the features of nodes and edges and exploring and analyzing the evolving SNNs to build insights into improving the EA.
AbstractList While Spiking Neural Networks (SNNs) show a lot of promise, it is difficult to optimize them because applying traditional gradient-based optimization techniques is difficult. Even though evolutionary algorithms (EAs) have been shown to promise to optimize SNNs, understanding the relationship between evolving the characteristics of SNNs and their performance to improve the optimization algorithm is challenging because of the complex characteristics and huge population size. We propose visual analytics with novel graph embedding for evolutionary SNNs to address the challenges. While existing graph embedding techniques have limitations in preserving the specific features of the nodes and edges, our approach maintains them. Also, we develop visual analytics for understanding the relationship between the network performance and the features of nodes and edges and exploring and analyzing the evolving SNNs to build insights into improving the EA.
Author Chae, Junghoon
Kulkarni, Shruti
Lim, Seung-Hwan
Schuman, Catherine
Author_xml – sequence: 1
  givenname: Junghoon
  surname: Chae
  fullname: Chae, Junghoon
  email: chaej@ornl.gov
  organization: Oak Ridge National Laboratory
– sequence: 2
  givenname: Seung-Hwan
  surname: Lim
  fullname: Lim, Seung-Hwan
  email: lims1@ornl.gov
  organization: Oak Ridge National Laboratory
– sequence: 3
  givenname: Shruti
  surname: Kulkarni
  fullname: Kulkarni, Shruti
  email: kulkarnisr@ornl.gov
  organization: Oak Ridge National Laboratory
– sequence: 4
  givenname: Catherine
  surname: Schuman
  fullname: Schuman, Catherine
  email: cschuman@utk.edu
  organization: University of Tennessee
BookMark eNotj89KxDAYxCPoQdd9A4W8QGvypUkab1Lq7sLSHqqehOVrm2rY_qPtKu7T26KX-TEwDDM35LLtWkvIPWc-58w87KI0yRQYzn1gEPiMMakuyNpoEwrJhAqVNNfkPUuSNzc-0llOWLuzaz_oZsD-k8ZNbsty8V1F46-uPk2ua3H4oWk_ucadcfG06gaa9e64BBN7GrCeMX13w3G8JVcV1qNd_3NFXp_jl2jr7dPNLnraewihnjxtEZgJbIgBQ7S5ZqUQCAUUleagQQZgQKAuuAh0IZXM8xDmH5oVBowFsSJ3f73OWnvoB9fMKw-caaWk4OIX6ghRdg
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICONS62911.2024.00056
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Xplore
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798350368659
EndPage 330
ExternalDocumentID 10766531
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-a287t-7ea2094e8a40aaeb70d33a2c2cf71272542923a7c1347c565bb8297970c929e23
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001462433900048&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 03:01:05 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a287t-7ea2094e8a40aaeb70d33a2c2cf71272542923a7c1347c565bb8297970c929e23
OpenAccessLink https://www.osti.gov/servlets/purl/2573544
PageCount 4
ParticipantIDs ieee_primary_10766531
PublicationCentury 2000
PublicationDate 2024-July-30
PublicationDateYYYYMMDD 2024-07-30
PublicationDate_xml – month: 07
  year: 2024
  text: 2024-July-30
  day: 30
PublicationDecade 2020
PublicationTitle 2024 International Conference on Neuromorphic Systems (ICONS)
PublicationTitleAbbrev ICONS
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.8911536
Snippet While Spiking Neural Networks (SNNs) show a lot of promise, it is difficult to optimize them because applying traditional gradient-based optimization...
SourceID ieee
SourceType Publisher
StartPage 327
SubjectTerms evolutionary algorithm
Evolutionary computation
Neuromorphics
Optimization
SNN
Spiking neural networks
Visual analytics
Title SNNVis: Visualizing Graph Embedding of Evolutionary Optimization for Spiking Neural Networks
URI https://ieeexplore.ieee.org/document/10766531
WOSCitedRecordID wos001462433900048&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/eLvHCXMwlZ07T8MwEMctqBiYAFHEWx5YDa6dxAlr1QJLWqmAOiBVZ_siVaIt6kuCT4_PDY-FgSWJ4iiRLnZ8d_Hvf4xdpZjnaJNUBHfXiyRBEGBbVlTaSdAk-O2qWGzClGU-HBb9GlaPLAwixsVneE2H8V--n7kVpcrCCDdZlhI1vW1MtoG1aiqnJYubh3avHGQqDN8Q9ylSxZZUl_pX1ZQ4aXT3_vm4fdb8we94_3tiOWBbOD1kL4OyfB4vbnnYEAj5EZr4HclN887EoqdL-azinXXdmWD-znvhgzCpSUse3FM-eBtTbpyTJge8hl1cBL5osqdu57F9L-rSCAJCiLMUBkGFwAxzSCQAWiO91qCccpVpKaNiFSoNxhEp6oLTZi0xtIWRLvhDqPQRa0xnUzxmPHEpVjKFXOoiqWQFIKXz4Qa28OClP2FNMs3obaN-Mfqyyukf58_YLlk_5j_lOWss5yu8YDtuvRwv5pfxnX0C6Ceayg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ1bS8MwFMeDTEGfVJx4Nw--VrM0XVpfx-aGsxtsyh6EcZKcwMBd2A3005tk9fLigy9taUoDuTTnnOZ3_oTcJJimqEQSOXPXREIgRKAqKrKxZhD7hN_aBrEJmefpYJB1C1g9sDCIGDaf4a2_DP_yzVSvfKjMzXBZrSaemt5OhOBsg2sVXE6FZXetWifvVbmbwM7z4z4vNvPK1L90U8Ky0dj_Z4UHpPwD4NHu99JySLZwckRee3n-MlrcU3fwKOSHK6IPPuE0rY8VGv8onVpaXxfDCebvtOM-CeOCtaTOQKW92chHx6nPygFv7hS2gS_K5LlR79eaUSGOEIFzcpaRRODONcMUBANAJZmJY-CaaysrXPKgQxWD1J4V1c5sU8pTtJlk2llEyONjUppMJ3hCqNAJWpZAyuJMWGYBGNPGvUBlBgwzp6Tsm2Y42-S_GH61ytkf96_JbrP_1B62W_njOdnzPRGioeyClJbzFV6SHb1ejhbzq9B_nyOinhE
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%3Abook&rft.genre=proceeding&rft.title=2024+International+Conference+on+Neuromorphic+Systems+%28ICONS%29&rft.atitle=SNNVis%3A+Visualizing+Graph+Embedding+of+Evolutionary+Optimization+for+Spiking+Neural+Networks&rft.au=Chae%2C+Junghoon&rft.au=Lim%2C+Seung-Hwan&rft.au=Kulkarni%2C+Shruti&rft.au=Schuman%2C+Catherine&rft.date=2024-07-30&rft.pub=IEEE&rft.spage=327&rft.epage=330&rft_id=info:doi/10.1109%2FICONS62911.2024.00056&rft.externalDocID=10766531