no code implementations • 28 Mar 2024 • Antonio Guerriero, Roberto Pietrantuono, Stefano Russo
Companies incur in high costs for testing DNN with datasets representative of the inputs expected in operation, as these need to be manually labelled.
no code implementations • 2 Mar 2023 • Antonio Guerriero, Roberto Pietrantuono, Stefano Russo
We propose DAIC (DNN Assessment and Improvement Cycle), an approach which combines ''low-cost'' online pseudo-oracles and ''high-cost'' offline sampling techniques to estimate and improve the operational accuracy of a DNN in the iterations of its life cycle.
1 code implementation • 8 Feb 2021 • Antonio Guerriero, Roberto Pietrantuono, Stefano Russo
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.
Software Engineering