Cornuéjols, AntoineAntoineCornuéjolsMurena, Pierre AlexandrePierre AlexandreMurenaOlivier, RaphaëlRaphaëlOlivier2023-04-252023-04-252020-0418th International Conference on Intelligent Data Analysis (IDA 2020)http://hdl.handle.net/11420/15243Using 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.en0302-97432020119131BoostingTransfer learningConference Paper10.1007/978-3-030-44584-3_10Conference Paper