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
Optimized Near-Zero Quantization Method for Flexible Memristor Based Neural Network
Fudan Univ, State Key Lab ASIC & Syst, Shanghai 200433, Peoples R China..
KTH, School of Electrical Engineering and Computer Science (EECS).
KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH).
Fudan Univ, State Key Lab ASIC & Syst, Shanghai 200433, Peoples R China..
Show others and affiliations
2018 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 6, p. 29320-29331Article in journal (Refereed) Published
Abstract [en]

Due to controllable conductance and non-volatility, flexible memristors are regarded as a key enabler for building artificial neural network (ANN)-based learning algorithms in flexible and wearable systems. However, the existing flexible memristors are suffering from limited number of conductance values, issues limiting large-scale integration, and insufficient accuracy that cannot support accurate computation of ANN. In this paper, solutions are proposed for the three major challenges of the flexible memristor; the feasibility of a three-layer fully connected neural network on MNIST and a 13-layer convolutional neural network (CNN) on CIFAR-10 using the flexible memristor based on single-walled carbon nanotubes network/polymer composite and hydrophilic Al2O3 dielectric are studied. The evaluation result shows that in the fully connected neural network system, it is able to recognize MNIST with an accuracy above 90% after 4-bit quantization, 52.05% decrease in interconnection numbers in the circuit and up to 40% random error introduced, and in the CNN on CIFAR-10, the system can retain an accuracy above 86% with less than 4% accuracy loss after 5-bit quantization, 59.34% decrease in interconnection numbers in the circuit and up to 40% random error injected.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2018. Vol. 6, p. 29320-29331
Keywords [en]
Artificial neural network, flexible memristor, near-zero optimizing, system resilience, weight quantization
National Category
Communication Systems
Identifiers
URN: urn:nbn:se:kth:diva-231644DOI: 10.1109/ACCESS.2018.2839106ISI: 000435521500013Scopus ID: 2-s2.0-85047177189OAI: oai:DiVA.org:kth-231644DiVA, id: diva2:1245049
Note

QC 20180904

Available from: 2018-09-04 Created: 2018-09-04 Last updated: 2018-10-22Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records BETA

Huan, YuxiangYang, Kunlong

Search in DiVA

By author/editor
Huan, YuxiangYang, Kunlong
By organisation
School of Electrical Engineering and Computer Science (EECS)School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH)
In the same journal
IEEE Access
Communication Systems

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 21 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