View in EDS

Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks.

Saved in:
Bibliographic Details
Title: Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks.
Authors: Gardner, Brian, Grüning, André
Source: Frontiers in Computational Neuroscience; 4/12/2021, Vol. 15, pN.PAG-N.PAG, 24p
Subject Terms: SUPERVISED learning, PROBLEM solving, NEURAL circuitry, INFORMATION processing, SYSTEMS theory
Abstract: Experimental studies support the notion of spike-based neuronal information processing in the brain, with neural circuits exhibiting a wide range of temporally-based coding strategies to rapidly and efficiently represent sensory stimuli. Accordingly, it would be desirable to apply spike-based computation to tackling real-world challenges, and in particular transferring such theory to neuromorphic systems for low-power embedded applications. Motivated by this, we propose a new supervised learning method that can train multilayer spiking neural networks to solve classification problems based on a rapid, first-to-spike decoding strategy. The proposed learning rule supports multiple spikes fired by stochastic hidden neurons, and yet is stable by relying on first-spike responses generated by a deterministic output layer. In addition to this, we also explore several distinct, spike-based encoding strategies in order to form compact representations of presented input data. We demonstrate the classification performance of the learning rule as applied to several benchmark datasets, including MNIST. The learning rule is capable of generalizing from the data, and is successful even when used with constrained network architectures containing few input and hidden layer neurons. Furthermore, we highlight a novel encoding strategy, termed "scanline encoding," that can transform image data into compact spatiotemporal patterns for subsequent network processing. Designing constrained, but optimized, network structures and performing input dimensionality reduction has strong implications for neuromorphic applications. [ABSTRACT FROM AUTHOR]
Copyright of Frontiers in Computational Neuroscience is the property of Frontiers Media S.A. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Biomedical Index
FullText Text:
  Availability: 0
CustomLinks:
  – Url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=search&db=pmc&term=1662-5188[TA]+AND+N.PAG[PG]+AND+2021[PDAT]
    Name: FREE - PubMed Central (ISSN based link)
    Category: fullText
    Text: Full Text
    Icon: https://imageserver.ebscohost.com/NetImages/iconPdf.gif
    MouseOverText: Check this PubMed for the article full text.
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edm&genre=article&issn=16625188&ISBN=&volume=15&issue=&date=20210412&spage=N.PAG&pages=&title=Frontiers in Computational Neuroscience&atitle=Supervised%20Learning%20With%20First-to-Spike%20Decoding%20in%20Multilayer%20Spiking%20Neural%20Networks.&aulast=Gardner%2C%20Brian&id=DOI:10.3389/fncom.2021.617862
    Name: Full Text Finder
    Category: fullText
    Text: Full Text Finder
    Icon: https://imageserver.ebscohost.com/branding/images/FTF.gif
    MouseOverText: Full Text Finder
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Gardner%20B
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edm
DbLabel: Biomedical Index
An: 150299895
RelevancyScore: 916
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 915.63525390625
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Gardner%2C+Brian%22">Gardner, Brian</searchLink><br /><searchLink fieldCode="AR" term="%22Grüning%2C+André%22">Grüning, André</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Frontiers in Computational Neuroscience; 4/12/2021, Vol. 15, pN.PAG-N.PAG, 24p
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22SUPERVISED+learning%22">SUPERVISED learning</searchLink><br /><searchLink fieldCode="DE" term="%22PROBLEM+solving%22">PROBLEM solving</searchLink><br /><searchLink fieldCode="DE" term="%22NEURAL+circuitry%22">NEURAL circuitry</searchLink><br /><searchLink fieldCode="DE" term="%22INFORMATION+processing%22">INFORMATION processing</searchLink><br /><searchLink fieldCode="DE" term="%22SYSTEMS+theory%22">SYSTEMS theory</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Experimental studies support the notion of spike-based neuronal information processing in the brain, with neural circuits exhibiting a wide range of temporally-based coding strategies to rapidly and efficiently represent sensory stimuli. Accordingly, it would be desirable to apply spike-based computation to tackling real-world challenges, and in particular transferring such theory to neuromorphic systems for low-power embedded applications. Motivated by this, we propose a new supervised learning method that can train multilayer spiking neural networks to solve classification problems based on a rapid, first-to-spike decoding strategy. The proposed learning rule supports multiple spikes fired by stochastic hidden neurons, and yet is stable by relying on first-spike responses generated by a deterministic output layer. In addition to this, we also explore several distinct, spike-based encoding strategies in order to form compact representations of presented input data. We demonstrate the classification performance of the learning rule as applied to several benchmark datasets, including MNIST. The learning rule is capable of generalizing from the data, and is successful even when used with constrained network architectures containing few input and hidden layer neurons. Furthermore, we highlight a novel encoding strategy, termed "scanline encoding," that can transform image data into compact spatiotemporal patterns for subsequent network processing. Designing constrained, but optimized, network structures and performing input dimensionality reduction has strong implications for neuromorphic applications. [ABSTRACT FROM AUTHOR]
– Name: Abstract
  Label:
  Group: Ab
  Data: <i>Copyright of Frontiers in Computational Neuroscience is the property of Frontiers Media S.A. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edm&AN=150299895
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3389/fncom.2021.617862
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 24
        StartPage: N.PAG
    Subjects:
      – SubjectFull: SUPERVISED learning
        Type: general
      – SubjectFull: PROBLEM solving
        Type: general
      – SubjectFull: NEURAL circuitry
        Type: general
      – SubjectFull: INFORMATION processing
        Type: general
      – SubjectFull: SYSTEMS theory
        Type: general
    Titles:
      – TitleFull: Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Gardner, Brian
      – PersonEntity:
          Name:
            NameFull: Grüning, André
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 12
              M: 04
              Text: 4/12/2021
              Type: published
              Y: 2021
          Identifiers:
            – Type: issn-print
              Value: 16625188
          Numbering:
            – Type: volume
              Value: 15
          Titles:
            – TitleFull: Frontiers in Computational Neuroscience
              Type: main
ResultId 1