City Research Online

Principles of Explanatory Debugging to personalize interactive machine learning

Kulesza, T., Burnett, M., Wong, W-K. & Stumpf, S. (2015). Principles of Explanatory Debugging to personalize interactive machine learning. In: Brdiczka, O. & Chau, P (Eds.), Proceedings of the 20th International Conference on Intelligent User Interfaces. (pp. 126-137). New York, USA: ACM. doi: 10.1145/2678025.2701399

Abstract

How can end users efficiently influence the predictions that machine learning systems make on their behalf? This paper presents Explanatory Debugging, an approach in which the system explains to users how it made each of its predictions, and the user then explains any necessary corrections back to the learning system. We present the principles underlying this approach and a prototype instantiating it. An empirical evaluation shows that Explanatory Debugging increased participants' understanding of the learning system by 52% and allowed participants to correct its mistakes up to twice as efficiently as participants using a traditional learning system.

Publication Type: Book Section
Additional Information: © Stumpf, S. et al | ACM 2015. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the 20th International Conference on Intelligent User Interfaces, http://dx.doi.org/10.1145/2678025.2701399
Publisher Keywords: Interactive machine learning; end user programming
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments: School of Science & Technology > Computer Science
[thumbnail of paper326.pdf]
Preview
Text - Accepted Version
Download (1MB) | Preview

Export

Add to AnyAdd to TwitterAdd to FacebookAdd to LinkedinAdd to PinterestAdd to Email

Downloads

Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login