Search Results for author: Manel Abdellatif

Found 4 papers, 2 papers with code

SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agents

no code implementations3 Aug 2023 Amirhossein Zolfagharian, Manel Abdellatif, Lionel C. Briand, Ramesh S

For practical reasons, SMARLA is designed to be black-box (as it does not require access to the internals of the agent) and leverages state abstraction to reduce the state space and thus facilitate the learning of safety violation prediction models from agent's states.


DeepGD: A Multi-Objective Black-Box Test Selection Approach for Deep Neural Networks

no code implementations8 Mar 2023 Zohreh Aghababaeyan, Manel Abdellatif, Mahboubeh Dadkhah, Lionel Briand

It reduces the cost of labeling by prioritizing the selection of test inputs with high fault revealing power from large unlabeled datasets.

Fault Detection speech-recognition +2

Cannot find the paper you are looking for? You can Submit a new open access paper.