no code implementations • 3 Nov 2022 • Kevin Zagalo, Olena Verbytska, Liliana Cucu-Grosjean, Avner Bar-Hen
In this paper, we propose a suited re-parametrization of the inverse Gaussian mixture distribution adapted to response times of real-time systems and the estimation of deadline miss probabilities.
no code implementations • 16 May 2022 • Fabien Furfaro, Avner Bar-Hen, Geoffroy Berthelot
The topology of artificial neural networks has a significant effect on their performance.
1 code implementation • NeurIPS 2019 • Charles Corbière, Nicolas Thome, Avner Bar-Hen, Matthieu Cord, Patrick Pérez
In this paper, we propose a new target criterion for model confidence, corresponding to the True Class Probability (TCP).
1 code implementation • NeurIPS 2019 • Charles Corbière, Nicolas Thome, Avner Bar-Hen, Matthieu Cord, Patrick Pérez
In this paper, we propose a new target criterion for model confidence, corresponding to the True Class Probability (TCP).
no code implementations • 22 Apr 2015 • Ehsan Variani, Kamel Lahouel, Avner Bar-Hen, Bruno Jedynak
The problem of target localization with noise is addressed.
no code implementations • 26 Jan 2015 • Pierre Barbillon, Sophie Donnet, Emmanuel Lazega, Avner Bar-Hen
In this paper, we extend the SBM to multiplex networks in order to obtain a clustering based on more than one kind of relationship.
Methodology