Zobraziť v EDS

Overview of the Neural Network Compression and Representation (NNR) Standard.

Uložené v:
Podrobná bibliografia
Názov: Overview of the Neural Network Compression and Representation (NNR) Standard.
Autori: Kirchhoffer, Heiner1 heiner.kirchhoffer@hhi.fraunhofer.de, Haase, Paul1, Samek, Wojciech1, Muller, Karsten1 karsten.mueller@hhi.fraunhofer.de, Rezazadegan-Tavakoli, Hamed2, Cricri, Francesco2, Aksu, Emre B.2, Hannuksela, Miska M.2, Jiang, Wei3, Wang, Wei3, Liu, Shan3, Jain, Swayambhoo4, Hamidi-Rad, Shahab4, Racape, Fabien4, Bailer, Werner5
Zdroj: IEEE Transactions on Circuits & Systems for Video Technology. May2022, Vol. 32 Issue 5, p3203-3216. 14p.
Predmety: *ARTIFICIAL neural networks, LINEAR network coding, NEURAL codes, BINARY codes, BIOLOGICAL neural networks
Abstrakt: Neural Network Coding and Representation (NNR) is the first international standard for efficient compression of neural networks (NNs). The standard is designed as a toolbox of compression methods, which can be used to create coding pipelines. It can be either used as an independent coding framework (with its own bitstream format) or together with external neural network formats and frameworks. For providing the highest degree of flexibility, the network compression methods operate per parameter tensor in order to always ensure proper decoding, even if no structure information is provided. The NNR standard contains compression-efficient quantization and deep context-adaptive binary arithmetic coding (DeepCABAC) as core encoding and decoding technologies, as well as neural network parameter pre-processing methods like sparsification, pruning, low-rank decomposition, unification, local scaling and batch norm folding. NNR achieves a compression efficiency of more than 97% for transparent coding cases, i.e. without degrading classification quality, such as top-1 or top-5 accuracies. This paper provides an overview of the technical features and characteristics of NNR. [ABSTRACT FROM AUTHOR]
Copyright of IEEE Transactions on Circuits & Systems for Video Technology is the property of IEEE 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.)
Databáza: Business Source Index
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:bsx&genre=article&issn=10518215&ISBN=&volume=32&issue=5&date=20220501&spage=3203&pages=3203-3216&title=IEEE Transactions on Circuits & Systems for Video Technology&atitle=Overview%20of%20the%20Neural%20Network%20Compression%20and%20Representation%20%28NNR%29%20Standard.&aulast=Kirchhoffer%2C%20Heiner&id=DOI:10.1109/TCSVT.2021.3095970
    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=Kirchhoffer%20H
    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: bsx
DbLabel: Business Source Index
An: 156718321
RelevancyScore: 1267
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1267.04724121094
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Overview of the Neural Network Compression and Representation (NNR) Standard.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Kirchhoffer%2C+Heiner%22">Kirchhoffer, Heiner</searchLink><relatesTo>1</relatesTo><i> heiner.kirchhoffer@hhi.fraunhofer.de</i><br /><searchLink fieldCode="AR" term="%22Haase%2C+Paul%22">Haase, Paul</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Samek%2C+Wojciech%22">Samek, Wojciech</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Muller%2C+Karsten%22">Muller, Karsten</searchLink><relatesTo>1</relatesTo><i> karsten.mueller@hhi.fraunhofer.de</i><br /><searchLink fieldCode="AR" term="%22Rezazadegan-Tavakoli%2C+Hamed%22">Rezazadegan-Tavakoli, Hamed</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Cricri%2C+Francesco%22">Cricri, Francesco</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Aksu%2C+Emre+B%2E%22">Aksu, Emre B.</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Hannuksela%2C+Miska+M%2E%22">Hannuksela, Miska M.</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Jiang%2C+Wei%22">Jiang, Wei</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22Wang%2C+Wei%22">Wang, Wei</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22Liu%2C+Shan%22">Liu, Shan</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22Jain%2C+Swayambhoo%22">Jain, Swayambhoo</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22Hamidi-Rad%2C+Shahab%22">Hamidi-Rad, Shahab</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22Racape%2C+Fabien%22">Racape, Fabien</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22Bailer%2C+Werner%22">Bailer, Werner</searchLink><relatesTo>5</relatesTo>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22IEEE+Transactions+on+Circuits+%26+Systems+for+Video+Technology%22">IEEE Transactions on Circuits & Systems for Video Technology</searchLink>. May2022, Vol. 32 Issue 5, p3203-3216. 14p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22ARTIFICIAL+neural+networks%22">ARTIFICIAL neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22LINEAR+network+coding%22">LINEAR network coding</searchLink><br /><searchLink fieldCode="DE" term="%22NEURAL+codes%22">NEURAL codes</searchLink><br /><searchLink fieldCode="DE" term="%22BINARY+codes%22">BINARY codes</searchLink><br /><searchLink fieldCode="DE" term="%22BIOLOGICAL+neural+networks%22">BIOLOGICAL neural networks</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Neural Network Coding and Representation (NNR) is the first international standard for efficient compression of neural networks (NNs). The standard is designed as a toolbox of compression methods, which can be used to create coding pipelines. It can be either used as an independent coding framework (with its own bitstream format) or together with external neural network formats and frameworks. For providing the highest degree of flexibility, the network compression methods operate per parameter tensor in order to always ensure proper decoding, even if no structure information is provided. The NNR standard contains compression-efficient quantization and deep context-adaptive binary arithmetic coding (DeepCABAC) as core encoding and decoding technologies, as well as neural network parameter pre-processing methods like sparsification, pruning, low-rank decomposition, unification, local scaling and batch norm folding. NNR achieves a compression efficiency of more than 97% for transparent coding cases, i.e. without degrading classification quality, such as top-1 or top-5 accuracies. This paper provides an overview of the technical features and characteristics of NNR. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of IEEE Transactions on Circuits & Systems for Video Technology is the property of IEEE 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=bsx&AN=156718321
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/TCSVT.2021.3095970
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 14
        StartPage: 3203
    Subjects:
      – SubjectFull: ARTIFICIAL neural networks
        Type: general
      – SubjectFull: LINEAR network coding
        Type: general
      – SubjectFull: NEURAL codes
        Type: general
      – SubjectFull: BINARY codes
        Type: general
      – SubjectFull: BIOLOGICAL neural networks
        Type: general
    Titles:
      – TitleFull: Overview of the Neural Network Compression and Representation (NNR) Standard.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Kirchhoffer, Heiner
      – PersonEntity:
          Name:
            NameFull: Haase, Paul
      – PersonEntity:
          Name:
            NameFull: Samek, Wojciech
      – PersonEntity:
          Name:
            NameFull: Muller, Karsten
      – PersonEntity:
          Name:
            NameFull: Rezazadegan-Tavakoli, Hamed
      – PersonEntity:
          Name:
            NameFull: Cricri, Francesco
      – PersonEntity:
          Name:
            NameFull: Aksu, Emre B.
      – PersonEntity:
          Name:
            NameFull: Hannuksela, Miska M.
      – PersonEntity:
          Name:
            NameFull: Jiang, Wei
      – PersonEntity:
          Name:
            NameFull: Wang, Wei
      – PersonEntity:
          Name:
            NameFull: Liu, Shan
      – PersonEntity:
          Name:
            NameFull: Jain, Swayambhoo
      – PersonEntity:
          Name:
            NameFull: Hamidi-Rad, Shahab
      – PersonEntity:
          Name:
            NameFull: Racape, Fabien
      – PersonEntity:
          Name:
            NameFull: Bailer, Werner
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 05
              Text: May2022
              Type: published
              Y: 2022
          Identifiers:
            – Type: issn-print
              Value: 10518215
          Numbering:
            – Type: volume
              Value: 32
            – Type: issue
              Value: 5
          Titles:
            – TitleFull: IEEE Transactions on Circuits & Systems for Video Technology
              Type: main
ResultId 1