Malmö University Publications
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
Mapping Knowledge Representations to Concepts: A Review and New Perspectives
Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT). Malmö University, Internet of Things and People (IOTAP).ORCID iD: 0000-0001-5676-1931
Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT). Malmö University, Internet of Things and People (IOTAP).ORCID iD: 0000-0003-0998-6585
Malmö University, Faculty of Culture and Society (KS), Collaborative Future Making (CFM). Malmö University, Faculty of Culture and Society (KS), School of Arts and Communication (K3). Malmö University, Internet of Things and People (IOTAP).ORCID iD: 0000-0001-8836-7373
2022 (English)In: Explainable Agency in Artificial Intelligence Workshop Proceedings, 2022, p. 61-70Conference paper, Published paper (Refereed)
Abstract [en]

The success of neural networks builds to a large extent on their ability to create internal knowledge representations from real-world high-dimensional data, such as images, sound, or text. Approaches to extract and present these representations, in order to explain the neural network's decisions, is an active and multifaceted research field. To gain a deeper understanding of a central aspect of this field, we have performed a targeted review focusing on research that aims to associate internal representations with human understandable concepts. In doing this, we added a perspective on the existing research by using primarily deductive nomological explanations as a proposed taxonomy. We find this taxonomy and theories of causality, useful for understanding what can be expected, and not expected, from neural network explanations. The analysis additionally uncovers an ambiguity in the reviewed literature related to the goal of model explainability; is it understanding the ML model or, is it actionable explanations useful in the deployment domain? 

Place, publisher, year, edition, pages
2022. p. 61-70
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:mau:diva-64797DOI: 10.48550/arXiv.2301.00189OAI: oai:DiVA.org:mau-64797DiVA, id: diva2:1823013
Conference
36th AAAI Conference on Artificial Intelligence, February 28-March 1 2022, Vancouver, Canada
Available from: 2023-12-29 Created: 2023-12-29 Last updated: 2023-12-29Bibliographically approved

Open Access in DiVA

fulltext(309 kB)31 downloads
File information
File name FULLTEXT01.pdfFile size 309 kBChecksum SHA-512
bbd76fa61dd477194579f667a6a0bff549c7ae31639342e65fcbfe0fdf193c58172f92fac2f6f4d69f51cbe4e38e03cbc500e560757c1a543e9e8eb2f1387417
Type fulltextMimetype application/pdf

Other links

Publisher's full textProceedings

Authority records

Holmberg, LarsDavidsson, PaulLinde, Per

Search in DiVA

By author/editor
Holmberg, LarsDavidsson, PaulLinde, Per
By organisation
Department of Computer Science and Media Technology (DVMT)Internet of Things and People (IOTAP)Collaborative Future Making (CFM)School of Arts and Communication (K3)
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 31 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

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 159 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