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
Associative memories realized as artificial neural networks with presynaptic inhibition
2001 (English)Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

This thesis examines a possibility to improve artificial associative memories and their capability to separate similar memories. This is accomplished by extending traditional associative memories with a recognition and inhibition net. Thereby there is a great improvement in the network's capability to handle memories with great resemblance. A learning rule for the extended network is also presented.

Place, publisher, year, edition, pages
2001.
Keyword [en]
Technology, associative memories, neural networks, presynaptic inhibition
Keyword [sv]
Teknik
Identifiers
URN: urn:nbn:se:ltu:diva-44586ISRN: LTU-EX--01/339--SELocal ID: 25e3a420-5917-4a66-b969-41f78d4efeacOAI: oai:DiVA.org:ltu-44586DiVA: diva2:1017865
Subject / course
Student thesis, at least 30 credits
Educational program
Electrical Engineering, master's level
Examiners
Note
Validerat; 20101217 (root)Available from: 2016-10-04 Created: 2016-10-04Bibliographically approved

Open Access in DiVA

No full text

Search outside of DiVA

GoogleGoogle Scholar

Total: 8 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