Domain adaptation is an effective solution to data scarcity in low-resource scenarios.
However, when applied to token-level tasks such as bioNER, domain adaptation methods …

Developing meta-learning algorithms that are un-biased toward a subset of training tasks
often requires hand-designed criteria to weight tasks, potentially resulting in sub-optimal …

Meta learning or learning to learn has been an attractive topic of research in the past years.
Different methods in this area have been proposed to solve existing problems in the …

This thesis is concerned with learning in distributed applications such as IoT, industry 4.0, or
connected health. We are interested in the different challenges, both theoretical and …

Settings Methods Episodic training Heterogeneous tasks single-input multi-output (SIMO)[1–
7]✗✗ multi-input multi-output (MIMO)[8–13]✗✓ conventional meta-learning[14–19]✓-multi …

Résumé Cette thèse porte sur l'apprentissage dans les applications distribuées telles que
l'IoT, l'industrie 4.0 ou la santé connectée. Nous nous intéressons aux différents défis, tant …

Meta learning has many different definitions, but it is generally known as learning to learn.
This term was first introduced in 1987 by Jürgen Schmidhuber in [1]. Works in the field of …