Dalarna University's logo and link to the university's website

du.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • 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
Understanding Memories of the Past in the Context of Different Complex Neural Network Architectures.
Michigan State University, Department of Integrative Biology and BEACON Center for the Study of Evolution in Action, East Lansing, U.S.A..
Michigan State University, BEACON Center for the Study of Evolution in Action and Department of Computer Science and Engineering, East Lansing, U.S.A.
Dalarna University, School of Information and Engineering, Microdata Analysis. Michigan State University, BEACON Center for the Study of Evolution in Action, East Lansing, U.S.A..ORCID iD: 0000-0002-4872-1961
2022 (English)In: Neural Computation, ISSN 0899-7667, E-ISSN 1530-888X, Vol. 34, no 3, p. 754-780Article in journal (Refereed) Published
Abstract [en]

Deep learning (primarily using backpropagation) and neuroevolution are the preeminent methods of optimizing artificial neural networks. However, they often create black boxes that are as hard to understand as the natural brains they seek to mimic. Previous work has identified an information-theoretic tool, referred to as R, which allows us to quantify and identify mental representations in artificial cognitive systems. The use of such measures has allowed us to make previous black boxes more transparent. Here we extend R to not only identify where complex computational systems store memory about their environment but also to differentiate between different time points in the past. We show how this extended measure can identify the location of memory related to past experiences in neural networks optimized by deep learning as well as a genetic algorithm.

Place, publisher, year, edition, pages
2022. Vol. 34, no 3, p. 754-780
Keywords [en]
Neural Networks, Computer; Brain
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:du-39350DOI: 10.1162/neco_a_01469ISI: 000759801900006PubMedID: 35016223Scopus ID: 2-s2.0-85125212645OAI: oai:DiVA.org:du-39350DiVA, id: diva2:1629612
Available from: 2022-01-18 Created: 2022-01-18 Last updated: 2023-04-14Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records

Hintze, Arend

Search in DiVA

By author/editor
Hintze, Arend
By organisation
Microdata Analysis
In the same journal
Neural Computation
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 478 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • 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