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

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 +
  • Employeur
    ÉCOLE NORMALE SUPERIEURE PARIS-SACLAY
  • Secteur d’activité de la structure
    Enseignement - Formation - Recherche
  • Effectif de la structure
    Plus de 250 salariés
  • Type de stage ou contrat
    Stage d'immersion en milieu professionnel dans le cadre de la formation professionnelle continue
  • Date prévisionnelle de démarrage
  • Durée du stage ou contrat
    Plus de 2 mois et jusqu'à 4 mois
  • Le stage est-il rémunéré ?
    Oui
  • Niveau de qualification requis

    Bac + 4/5 et +
  • Lieu du stage
    ENS Paris-Saclay
    4 Avenue des Sciences
    91190 GIF SUR YVETTE
  • Accès et transports
    RER 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)