Skip to Main content Skip to Navigation
Journal articles

Challenges in Evaluating Interactive Visual Machine Learning Systems

Abstract : In interactive visual machine learning (IVML), humans and machine learning algorithms collaborate to achieve tasks mediated by interactive visual interfaces. This human-in-the-loop approach to machine learning brings forth not only numerous intelligibility, trust and usability issues, but also many open questions with respect to the evaluation of the IVML system, both as separate components, and as a holistic entity that includes both human and machine intelligence. This article describes the challenges and research gaps identified in an IEEE VIS workshop on the evaluation of interactive visual machine learning systems.
Document type :
Journal articles
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03133986
Contributor : Anastasia Bezerianos Connect in order to contact the contributor
Submitted on : Monday, February 8, 2021 - 12:19:49 AM
Last modification on : Wednesday, April 27, 2022 - 3:58:02 AM
Long-term archiving on: : Sunday, May 9, 2021 - 6:14:30 PM

File

CGnA_EVIVA_ML.pdf
Files produced by the author(s)

Identifiers

Citation

Nadia Boukhelifa, Anastacia Bezerianos, Remco Chang, Christopher Collins, Steven Drucker, et al.. Challenges in Evaluating Interactive Visual Machine Learning Systems. IEEE Computer Graphics and Applications, Institute of Electrical and Electronics Engineers, 2020, 40 (6), pp.88-96. ⟨10.1109/MCG.2020.3017064⟩. ⟨hal-03133986⟩

Share

Metrics

Record views

75

Files downloads

154