https://www.mdu.se/

mdu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
ΔnN: Power-Efficient Neural Network Acceleration Using Differential Weights
Univ Tehran, Dept Elect & Comp Engn, Comp Engn, Tehran, Iran..
Univ Tehran, Tehran, Iran..
Univ Tehran, Dept Elect & Comp Engn, Comp Engn, Tehran, Iran..
Univ Tehran, Coll Engn, Dept Elect & Comp Engn, Tehran, Iran..
Show others and affiliations
2020 (English)In: IEEE Micro, ISSN 0272-1732, E-ISSN 1937-4143, Vol. 40, no 1, p. 67-74Article in journal (Refereed) Published
Abstract [en]

The enormous and ever-increasing complexity of state-of-the-art neural networks has impeded the deployment of deep learning on resource-limited embedded and mobile devices. To reduce the complexity of neural networks, this article presents Delta NN, a power-efficient architecture that leverages a combination of the approximate value locality of neuron weights and algorithmic structure of neural networks. Delta NN keeps each weight as its difference (Delta) to the nearest smaller weight: each weight reuses the calculations of the smaller weight, followed by a calculation on the Delta value to make up the difference. We also round up/down the Delta to the closest power of two numbers to further reduce complexity. The experimental results show that Delta NN boosts the average performance by 14%-37% and reduces the average power consumption by 17%-49% over some state-of-the-art neural network designs.

Place, publisher, year, edition, pages
IEEE COMPUTER SOC , 2020. Vol. 40, no 1, p. 67-74
National Category
Communication Systems
Identifiers
URN: urn:nbn:se:mdh:diva-47029DOI: 10.1109/MM.2019.2948345ISI: 000508573000010Scopus ID: 2-s2.0-85073748116OAI: oai:DiVA.org:mdh-47029DiVA, id: diva2:1392885
Available from: 2020-02-13 Created: 2020-02-13 Last updated: 2020-02-20Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Daneshtalab, Masoud

Search in DiVA

By author/editor
Daneshtalab, Masoud
By organisation
Embedded Systems
In the same journal
IEEE Micro
Communication Systems

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 110 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf