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...

Celý popis

Podrobná bibliografia

Vydané v:	Proceedings / International Conference on Software Engineering s. 348 - 358
Hlavní autori:	Guerriero, Antonio, Pietrantuono, Roberto, Russo, Stefano
Médium:	Konferenčný príspevok..
Jazyk:	English
Vydavateľské údaje:	IEEE 01.05.2021
Predmet:	Adaptation models Artificial Neural Networks Computer bugs Labeling Neural networks Software Software engineering Software testing Testing
ISBN:	1665402962, 9781665402965
ISSN:	1558-1225
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!