Search: onr:"swepub:oai:DiVA.org:mau-18380" >
Evaluating Interpre...
Evaluating Interpretability in Machine Teaching
-
- Holmberg, Lars (author)
- Malmö universitet,Institutionen för datavetenskap och medieteknik (DVMT)
-
- Davidsson, Paul (author)
- Malmö universitet,Institutionen för datavetenskap och medieteknik (DVMT)
-
- Linde, Per (author)
- Malmö universitet,Institutionen för konst, kultur och kommunikation (K3)
-
(creator_code:org_t)
- 2020-07-06
- 2020
- English.
-
In: Highlights in Practical Applications of Agents, Multi-Agent Systems, and Trust-worthiness. - Cham : Springer. - 9783030519988 - 9783030519995 ; , s. 54-65
- Related links:
-
https://mau.diva-por... (primary) (Raw object)
-
show more...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Building interpretable machine learning agents is a challenge that needs to be addressed to make the agents trustworthy and align the usage of the technology with human values. In this work, we focus on how to evaluate interpretability in a machine teaching setting, a settingthat involves a human domain expert as a teacher in relation to a machine learning agent. By using a prototype in a study, we discuss theinterpretability denition and show how interpretability can be evaluatedon a functional-, human- and application level. We end the paperby discussing open questions and suggestions on how our results can be transferable to other domains.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Människa-datorinteraktion (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Human Computer Interaction (hsv//eng)
Keyword
- Interaktionsdesign
- Interaktionsdesign
Publication and Content Type
- vet (subject category)
- kon (subject category)
Find in a library
To the university's database