Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
A multiplication reduction technique with near-zero approximation for embedded learning in IoT devices
KTH.
KTH, Skolan för informations- och kommunikationsteknik (ICT), Elektronik, Integrerade komponenter och kretsar. Fudan University, China.
Visa övriga samt affilieringar
2017 (Engelska)Ingår i: International System on Chip Conference, IEEE Computer Society , 2017, s. 102-107Konferensbidrag (Refereegranskat)
Abstract [en]

This paper presents a multiplication reduction technique through near-zero approximation, enabling embedded learning in resource-constrained IoT devices. The intrinsic resilience of neural network and the sparsity of data are identified and utilized. Based on the analysis of leading zero counting and adjustable threshold, intentional approximation is applied to reduce near-zero multiplications. By setting the threshold of the multiplication result to 2-5 and employing ReLU as the neuron activation function, the sparsity of the CNN model can reach 75% with negligible loss in accuracy when recognizing the MNIST data set. Corresponding hardware implementation has been designed and simulated in UMC 65nm process. It can achieve more than 70% improvement of energy efficiency with only 0.37% area overhead of a 256 Multiply-Accumulator array.

Ort, förlag, år, upplaga, sidor
IEEE Computer Society , 2017. s. 102-107
Nyckelord [en]
Energy efficiency, Hardware, Programmable logic controllers, Area overhead, CNN models, Data set, Embedded learning, Hardware implementations, Multiply accumulators, Neuron activation function, Reduction techniques, Internet of things
Nationell ämneskategori
Elektroteknik och elektronik
Identifikatorer
URN: urn:nbn:se:kth:diva-216527DOI: 10.1109/SOCC.2016.7905445ISI: 000403576000018Scopus ID: 2-s2.0-85019109259ISBN: 9781509013661 (tryckt)OAI: oai:DiVA.org:kth-216527DiVA, id: diva2:1161802
Konferens
29th IEEE International System on Chip Conference, SOCC 2016, 6 September 2016 through 9 September 2016
Anmärkning

QC 20171201

Tillgänglig från: 2017-12-01 Skapad: 2017-12-01 Senast uppdaterad: 2017-12-01Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Sök vidare i DiVA

Av författaren/redaktören
You, YantianZheng, LirongZou, Zhuo
Av organisationen
KTHIntegrerade komponenter och kretsar
Elektroteknik och elektronik

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 109 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf