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
A Comparative Study of Routing Methods in Capsule Networks
Linköping University, Department of Electrical Engineering, Computer Vision.
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Recently, the deep neural network structure caps-net was proposed by Sabouret al. [11]. Capsule networks are designed to learn relative geometry betweenthe features of a layer and the features of the next layer. The Capsule network’smain building blocks are capsules, which are represented by vectors. The ideais that each capsule will represent a feature as well as traits or subfeatures ofthat feature. This allows for smart information routing. Capsules traits are usedto predict the traits of the capsules in the next layer, and information is sent toto next layer capsules on which the predictions agree. This is called routing byagreement.This thesis investigates theoretical support of new and existing routing al-gorithms as well as evaluates their performance on the MNIST [16] and CIFAR-10 [8] datasets. A variation of the dynamic routing algorithm presented in theoriginal paper [11] achieved the highest accuracy and fastest execution time.

Place, publisher, year, edition, pages
2019. , p. 90
Keywords [en]
Computer Vision, Deep Learning, Capsule Networks
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:liu:diva-156673ISRN: LiTH-ISY-EX--19/5188--SEOAI: oai:DiVA.org:liu-156673DiVA, id: diva2:1314210
External cooperation
SICK Linköping
Subject / course
Computer Vision Laboratory
Presentation
2019-02-15, Systemet, 581 83, Linköping, 09:00 (English)
Supervisors
Examiners
Available from: 2019-05-08 Created: 2019-05-07 Last updated: 2019-05-08Bibliographically approved

Open Access in DiVA

fulltext(1565 kB)133 downloads
File information
File name FULLTEXT01.pdfFile size 1565 kBChecksum SHA-512
cbf5baca6627523ae3ec91394129fb14ad3847cc6d306a5d1b5eb524577312b78c11739eef85603412c335120d2a72e14721627d2a6c8cdf43bfd6a01441682e
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Malmgren, Christoffer
By organisation
Computer Vision
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar
Total: 133 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 403 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