Aller au contenu
Accueil TechPourToutes Programme
Retour

Seras-tu la prochaine stagiaire de ÉCOLE NORMALE SUPERIEURE PARIS-SACLAY ?

Study of the impact of domain shift assumptions on transfer learning methods

Informatique pour la recherche

Offre mise à jour le 28 mars 2024

Type d’offre :
Stage dans le supérieur
Durée :
non indiqué
Niveau d’expérience :
non indiqué
Salaire :
non indiqué
Entreprise :
ÉCOLE NORMALE SUPERIEURE PARIS-SACLAY
Secteur :
non indiqué
Adresse
ENS Paris-Saclay, 91190 St Aubin

Descriptif de l’offre

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

Cette offre ID gsR658jHTS9k4r3Fg a été publiée le 14 juin 2023 sur le site de notre partenaire, MyFuture.