Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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
Biologically inspired system for visual concept learning
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering.
2018 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

This thesis showcases how computer vision and artificial intelligencecan be combined to a system that is able to navigate surroundings byintercepting visual stimulants.The system is built to operate on signs which displays eight colored shapeswere different patterns of shapes will direct the user. When a sign is in-tercepted by the system, the shapes and their spatial positioning will beextracted with the help of computer vision and be processed by a modelof computation known as Vector Symbolic Architectures. This model of-fers a way to learn and reason about the patterns which leads to certainlocations. It uses high dimensional vectors to represent entities such ascolors, shapes and positions and with the help of basic mathematical op-erations provides the ability to produce vectors that represents conceptsconstructed of many such entities. Because of this representation it ispossible to preform classification and provide guidance based on the sim-ilarities of previous collected concepts.This paper will focus on the practical details of how such a Vector Sym-bolic Architecture model can be implemented and how it is able to providethe functionality for a navigation system.

Place, publisher, year, edition, pages
2018. , p. 22
Keywords [en]
Vector Symbolic Architecture
National Category
Computer Systems
Identifiers
URN: urn:nbn:se:ltu:diva-71504OAI: oai:DiVA.org:ltu-71504DiVA, id: diva2:1261554
Educational program
Computer Engineering, bachelor's level
Supervisors
Examiners
Available from: 2018-11-21 Created: 2018-11-07 Last updated: 2018-11-21Bibliographically approved

Open Access in DiVA

No full text in DiVA

Search in DiVA

By author/editor
Sundström, Erik
By organisation
Department of Computer Science, Electrical and Space Engineering
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 77 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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