Sort by
Refine Your Search
-
Category
-
Program
-
Employer
- Nature Careers
- Ecole Centrale de Nantes
- Institut Pasteur
- Université de Lorraine
- CNRS
- Institut Curie - PSL
- NeuroSchool, Aix-Marseille Université
- Université d'Orléans
- Université de Lille
- INSA Strasbourg
- Inria, the French national research institute for the digital sciences
- Oniris VetAgrobio Nantes
- Télécom Paris
- Université Toulouse III Paul Sabatier
- Université du Littoral Côte d'Opale
- 5 more »
- « less
-
Field
-
computational framework, integrated with deep reinforcement learning (DRL) methodologies for both gene-level and edge-level perturbation control, represents a significant advancement in the computational toolkit
-
. ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------------------------------------...
-
level of performance. Expected research should focus on developing more sophisticated learning frameworks, particularly through the integration of deep reinforcement learning. The first part of the thesis
-
Inria, the French national research institute for the digital sciences | Montpellier, Languedoc Roussillon | France | 3 months ago
/public/classic/en/offres/2025-08683 Requirements Skills/Qualifications Python programming. Deep Learning with Python (preferably with Pytorch). Experience with GIS. Experience with NLP would be a plus
-
. Côte d’Azur & INRIA), will be focused on the development and the understanding of deep latent variables models for unsupervised learning with massive heterogenous data. Although deep learning methods and
-
the understanding of deep latent variables models for unsupervised learning with massive and evolving heterogenous data. Although deep learning methods and their statistical extensions, the deep latent
-
rank models [Sportisse et al., 2020], random forests [Stekhoven and Buhlmann, 2012] or deep learning techniques with variational autoencoders [Mattei and Frellsen, 2019, Ipsen et al., 2021]. One
-
of specialized deep learning models (neural network or transformer) for automated segmentation of tibial plateau fractures. iii) The algorithm must then be trained to allow it to learn the morphologies of bone
-
, are discriminant). In particular, point i) undermines most of the recent deep learning machinery used for shapes classification [e.g. PointNet Qi et al., 2017], even if one wished to adopt them for simple feature
-
on their vulnerabilities against those attacks. While, the existing recent literature on the study of such attacks for FL mostly concentrates on deep learning. The PhD candidate will also investigate different ML algorithms