Transfer Learning by Learning Projections from Target to Source - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Transfer Learning by Learning Projections from Target to Source

Résumé

Using transfer learning to help in solving a new classification task where labeled data is scarce is becoming popular. Numerous experiments with deep neural networks, where the representation learned on a source task is transferred to learn a target neural network, have shown the benefits of the approach. This paper, similarly, deals with hypothesis transfer learning. However, it presents a new approach where, instead of transferring a representation, the source hypothesis is kept and this is a translation from the target domain to the source domain that is learned. In a way, a change of representation is learned. We show how this method performs very well on a classification of time series task where the space of time series is changed between source and target.

Mots clés

Fichier principal
Vignette du fichier
Cornuéjols2020_Chapter_TransferLearningByLearningProj.pdf (2.69 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03650261 , version 1 (24-04-2022)

Identifiants

Citer

Antoine Cornuéjols, Pierre-Alexandre Murena, Raphaël Olivier. Transfer Learning by Learning Projections from Target to Source. International Symposium on Intelligent Data Analysis, Apr 2020, Constance, Germany. pp.119 - 131, ⟨10.1007/978-3-030-44584-3_10⟩. ⟨hal-03650261⟩
36 Consultations
50 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More