Umeå University's logo

umu.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Density Encoding Enables Resource-Efficient Randomly Connected Neural Networks
Redwood Center for Theoretical Neuroscience, University of California at Berkeley, CA, Berkeley, United States; Intelligent Systems Lab, Research Institutes of Sweden, Kista, Sweden.
Netlight Consulting AB, Stockholm, Sweden.
Redwood Center for Theoretical Neuroscience, University of California at Berkeley, CA, Berkeley, United States.
Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.ORCID-id: 0000-0002-1313-0934
Vise andre og tillknytning
2021 (engelsk)Inngår i: IEEE Transactions on Neural Networks and Learning Systems, ISSN 2162-237X, E-ISSN 2162-2388, Vol. 32, nr 8, s. 3777-3783, artikkel-id 9174774Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

The deployment of machine learning algorithms on resource-constrained edge devices is an important challenge from both theoretical and applied points of view. In this brief, we focus on resource-efficient randomly connected neural networks known as random vector functional link (RVFL) networks since their simple design and extremely fast training time make them very attractive for solving many applied classification tasks. We propose to represent input features via the density-based encoding known in the area of stochastic computing and use the operations of binding and bundling from the area of hyperdimensional computing for obtaining the activations of the hidden neurons. Using a collection of 121 real-world data sets from the UCI machine learning repository, we empirically show that the proposed approach demonstrates higher average accuracy than the conventional RVFL. We also demonstrate that it is possible to represent the readout matrix using only integers in a limited range with minimal loss in the accuracy. In this case, the proposed approach operates only on small ${n}$ -bits integers, which results in a computationally efficient architecture. Finally, through hardware field-programmable gate array (FPGA) implementations, we show that such an approach consumes approximately 11 times less energy than that of the conventional RVFL.

sted, utgiver, år, opplag, sider
IEEE, 2021. Vol. 32, nr 8, s. 3777-3783, artikkel-id 9174774
Emneord [en]
Density-based encoding, hyperdimensional computing, random vector functional link (RVFL) networks
HSV kategori
Identifikatorer
URN: urn:nbn:se:umu:diva-186635DOI: 10.1109/TNNLS.2020.3015971ISI: 000681169500047PubMedID: 32833655Scopus ID: 2-s2.0-85112022593OAI: oai:DiVA.org:umu-186635DiVA, id: diva2:1589206
Forskningsfinansiär
Swedish Research Council, 2015-04677Tilgjengelig fra: 2021-08-30 Laget: 2021-08-30 Sist oppdatert: 2022-05-10bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstPubMedScopusFree full text in ArXiv

Person

Wiklund, Urban

Søk i DiVA

Av forfatter/redaktør
Wiklund, Urban
Av organisasjonen
I samme tidsskrift
IEEE Transactions on Neural Networks and Learning Systems

Søk utenfor DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric

doi
pubmed
urn-nbn
Totalt: 133 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf