Play MNIST For Me! User Studies on the Effects of Post-Hoc, Example-Based Explanations & Error Rates on Debugging a Deep Learning, Black-Box Classifier

Autor:	Ford, Courtney, Kenny, Eoin M., Keane, Mark T.
Rok vydání:	2020
Předmět:	Computer Science - Machine Learning Computer Science - Human-Computer Interaction I.2.8 F.2.2
Zdroj:	IJCAI-20 Workshop on Explainable AI (XAI), September 2020
Druh dokumentu:	Working Paper
Popis:	This paper reports two experiments (N=349) on the impact of post hoc explanations by example and error rates on peoples perceptions of a black box classifier. Both experiments show that when people are given case based explanations, from an implemented ANN CBR twin system, they perceive miss classifications to be more correct. They also show that as error rates increase above 4%, people trust the classifier less and view it as being less correct, less reasonable and less trustworthy. The implications of these results for XAI are discussed. Comment: 2 Figures, 1 Table, 8 pages
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2009.06349 Zobrazit plný text záznamu View this record from Arxiv