Challenging users’ perceptions of decision boundaries in machine learning systems

Work in Progress
Rob Bowman; Luke Church

We investigate the design of smart systems that drive the exploration of decision boundaries created by Machine Learning (ML). We are interested in users’ perceptions of decision boundaries, particularly in scenarios that involve the categorisation of non-categorical data. We present a system for colour categorisation using active learning with decision boundary visualisation and functionality for investigating users’ perceptions of the decision boundaries they are teaching the system.

Type of Publication: Paper
Conference: PPIG 2019 - 30th Annual Conference
Publication Year: 2019
TitleChallenging users’ perceptions of decision boundaries in machine learning systems
Publication TypePaper
AuthorsBowman, R, Church, L
PPIG Workshop: 
2019-08-30th