Partagez sur
STAGE Study of the impact of domain shift assumptions on transfer learning methods
Date de mise à jour de l’offre
ÉCOLE NORMALE SUPERIEURE PARIS-SACLAY :
L'École normale supérieure Paris-Saclay est une institution universitaire française d’enseignement supérieur et de recherche, établissement-composante de l'université Paris- Saclay, située sur le plateau de Saclay, dans l'Essonne.
Description de la mission
In classical machine learning, one assumes that the source data used to train an algorithm comes from the same distribution as the target data it is applied to. This assumption is not true for many applications: for instance, a human activity recognition model trained on young people may not perform well when applied to older ones [1]. This kind of distribution shift issue happen in numerous real scenario of machine learning applications and often degrade the model performance. To correct these shifts, different machine learning approaches have been developed within the field of domain adaptation or transfer learning [2].
Within the framework of the industrial chair IDAML [3] of ENS Paris-Saclay, a library of transfer learning methods, ADAPT [4], has been developed to facilitate the access of these techniques to the industrial sector.
Based on the library already developed, the project will consist in studying the dependence of the different transfer learning methods on their main hypotheses. This will allow to identify in which context each method can be efficiently applied and which type of method is to be preferred according to the nature of the problem. This work will thus help industrials to more easily identify which tool is best suited to their problems.
[1] https://www.ensiie.fr/wp- content/uploads/2020/10/PosterLudovicMinvielle-1.pdf
[2] Yishay Mansour, Mehryar Mohri, and Afshin Rostamizadeh. “Domain adaptation: Learning bounds and algorithms. In COLT, 2009.
[3] https://www.centreborelli.fr/partenariats/chaires/chaires-industrielles-2/
[4] https://github.com/adapt-python/adapt
Within the framework of the industrial chair IDAML [3] of ENS Paris-Saclay, a library of transfer learning methods, ADAPT [4], has been developed to facilitate the access of these techniques to the industrial sector.
Based on the library already developed, the project will consist in studying the dependence of the different transfer learning methods on their main hypotheses. This will allow to identify in which context each method can be efficiently applied and which type of method is to be preferred according to the nature of the problem. This work will thus help industrials to more easily identify which tool is best suited to their problems.
[1] https://www.ensiie.fr/wp- content/uploads/2020/10/PosterLudovicMinvielle-1.pdf
[2] Yishay Mansour, Mehryar Mohri, and Afshin Rostamizadeh. “Domain adaptation: Learning bounds and algorithms. In COLT, 2009.
[3] https://www.centreborelli.fr/partenariats/chaires/chaires-industrielles-2/
[4] https://github.com/adapt-python/adapt
Profil recherché
Required knowledge: deep learning (neural networks, transfer learning), numerical schemes for solving PDEs. Programming language: Python Formation: M2 student or gap year student M1, M2 in applied mathematics.
Niveau de qualification requis
Bac + 4/5 et +
Les offres de stage ou de contrat sont définies par les recruteurs eux-mêmes.
En sa qualité d’hébergeur dans le cadre du dispositif des « 100 000 stages », la Région Île-de-France est soumise à un régime de responsabilité atténuée prévu aux articles 6.I.2 et suivants de la loi n°2204-575 du 21 juin 2004 sur la confiance dans l’économie numérique.
La Région Île-de-France ne saurait être tenue responsable du contenu des offres.
Néanmoins, si vous détectez une offre frauduleuse, abusive ou discriminatoire vous pouvez la signaler
en cliquant sur ce lien.
-
EmployeurÉCOLE NORMALE SUPERIEURE PARIS-SACLAY
-
Secteur d’activité de la structureEnseignement - Formation - Recherche
-
Effectif de la structurePlus de 250 salariés
-
Type de stage ou contratStage d'immersion en milieu professionnel dans le cadre de la formation professionnelle continue
-
Date prévisionnelle de démarrage
-
Durée du stage ou contratPlus de 2 mois et jusqu'à 4 mois
-
Le stage est-il rémunéré ?Oui
-
Niveau de qualification requis
Bac + 4/5 et + -
Lieu du stageENS Paris-Saclay
4 Avenue des Sciences
91190 GIF SUR YVETTE -
Accès et transportsRER B (Saint-Rémy-lès-Chevreuse) ou RER C (Massy- Palaiseau) Arrêt : « Massy-Palaiseau » Puis prendre un des bus suivants :- Bus 91.06C (Christ de Saclay) - Bus 91.06B (Saint-Quentin-en-Yvelines)