Operation is the Hardest Teacher: Estimating DNN Accuracy Looking for Mispredictions

Deep Neural Networks (DNN) are typically tested for accuracy relying on a set of unlabelled real world data (operational dataset), from which a subset is selected, manually labelled and used as test suite. This subset is required to be small (due to manual labelling cost) yet to faithfully represent...

Full description

Bibliographic Details

Published in:	Proceedings / International Conference on Software Engineering pp. 348 - 358
Main Authors:	Guerriero, Antonio, Pietrantuono, Roberto, Russo, Stefano
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.05.2021
Subjects:	Adaptation models Artificial Neural Networks Computer bugs Labeling Neural networks Software Software engineering Software testing Testing
ISBN:	1665402962, 9781665402965
ISSN:	1558-1225
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!