no code implementations • 1 Apr 2024 • Houssem Ben Braiek, Foutse khomh
This chapter explores the foundational concept of robustness in Machine Learning (ML) and its integral role in establishing trustworthiness in Artificial Intelligence (AI) systems.
1 code implementation • 23 Aug 2023 • Ahmed Haj Yahmed, Rached Bouchoucha, Houssem Ben Braiek, Foutse khomh
Dr. DRL successfully helps agents to adapt to 19. 63% of drifted environments left unsolved by vanilla CL while maintaining and even enhancing by up to 45% the obtained rewards for drifted environments that are resolved by both approaches.
no code implementations • 7 Sep 2022 • Houssem Ben Braiek, Ali Tfaily, Foutse khomh, Thomas Reid, Ciro Guida
Hybrid surrogate optimization maintains high results quality while providing rapid design assessments when both the surrogate model and the switch mechanism for eventually transitioning to the HF model are calibrated properly.
no code implementations • 7 Sep 2022 • Houssem Ben Braiek, Thomas Reid, Foutse khomh
In the context of aircraft system performance assessment, deep learning technologies allow to quickly infer models from experimental measurements, with less detailed system knowledge than usually required by physics-based modeling.
no code implementations • 13 Jul 2022 • Ahmed Haj Yahmed, Houssem Ben Braiek, Foutse khomh, Sonia Bouzidi, Rania Zaatour
Quantization is one of the most applied Deep Neural Network (DNN) compression strategies, when deploying a trained DNN model on an embedded system or a cell phone.
1 code implementation • 1 Apr 2022 • Houssem Ben Braiek, Foutse khomh
All these model training steps can be error-prone.
no code implementations • 28 Jul 2021 • Ettore Merlo, Mira Marhaba, Foutse khomh, Houssem Ben Braiek, Giuliano Antoniol
We investigate the distribution of computational profile likelihood of metamorphic test cases with respect to the likelihood distributions of training, test and error control cases.
1 code implementation • 1 Jan 2021 • Amin Nikanjam, Mohammad Mehdi Morovati, Foutse khomh, Houssem Ben Braiek
To allow for the automatic detection of faults in DRL programs, we have defined a meta-model of DRL programs and developed DRLinter, a model-based fault detection approach that leverages static analysis and graph transformations.
no code implementations • 5 Sep 2019 • Houssem Ben Braiek, Foutse khomh
To overcome these limitations, we propose, DeepEvolution, a novel search-based approach for testing DL models that relies on metaheuristics to ensure a maximum diversity in generated test cases.
no code implementations • 5 Sep 2019 • Houssem Ben Braiek, Foutse khomh
In this paper, we examine training issues in ML programs and propose a catalog of verification routines that can be used to detect the identified issues, automatically.