Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Neural Distributed Autoassociative Memories: A Survey
International Research and Training Center for Information Technologies and Systems of the NAS of Ukraine and of Ministry of Education and Science of Ukraine.
International Research and Training Center for Information Technologies and Systems of the NAS of Ukraine and of Ministry of Education and Science of Ukraine.
Technical University of Ostrava.
Visa övriga samt affilieringar
2017 (Engelska)Ingår i: Cybernetics and Computer Engineering Journal, ISSN 0454-9910, Vol. 188, nr 2, s. 5-35Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

Introduction. Neural network models of autoassociative, distributed memory allow storage and retrieval of many items (vectors) where the number of stored items can exceed the vector dimension (the number of neurons in the network). This opens the possibility of a sublinear time search (in the number of stored items) for approximate nearest neighbors among vectors of high dimension.

The purpose of this paper is to review models of autoassociative, distributed memory that can be naturally implemented by neural networks (mainly with local learning rules and iterative dynamics based on information locally available to neurons).

Scope. The survey is focused mainly on the networks of Hopfield, Willshaw and Potts, that have connections between pairs of neurons and operate on sparse binary vectors. We discuss not only autoassociative memory, but also the generalization properties of these networks. We also consider neural networks with higher-order connections and networks with a bipartite graph structure for non-binary data with linear constraints.

Conclusions. In conclusion we discuss the relations to similarity search, advantages and drawbacks of these techniques, and topics for further research. An interesting and still not completely resolved question is whether neural autoassociative memories can search for approximate nearest neighbors faster than other index structures for similarity search, in particular for the case of very high dimensional vectors. 

Ort, förlag, år, upplaga, sidor
NASU-National Academy of Sciences of Ukraine , 2017. Vol. 188, nr 2, s. 5-35
Nationell ämneskategori
Datorsystem Datavetenskap (datalogi)
Forskningsämne
Kommunikations- och beräkningssystem
Identifikatorer
URN: urn:nbn:se:ltu:diva-66595DOI: 10.15407/kvt188.02.005OAI: oai:DiVA.org:ltu-66595DiVA, id: diva2:1157449
Tillgänglig från: 2017-11-16 Skapad: 2017-11-16 Senast uppdaterad: 2018-11-20Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltext

Personposter BETA

Kleyko, DenisOsipov, Evgeny

Sök vidare i DiVA

Av författaren/redaktören
Kleyko, DenisOsipov, Evgeny
Av organisationen
Datavetenskap
DatorsystemDatavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 103 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf