In this paper we summarize the contributions of participants to the third Sussex-Huawei
Locomotion-Transportation (SHL) Recognition Challenge organized at the HASCA …

In a large domain of classification problems for real applications, like human activity
recognition, separable spaces between groups of concepts are easier to learn than each …

Smartphone-sensors-based human activity recognition is attracting increasing interest due
to the popularization of smartphones. It is a difficult long-range temporal recognition …

The relative position of sensors placed on specific body parts generates two types of data
related to (1) the movement of the body part wrt the body and (2) the whole body wrt the …

Abstract In Internet of Things applications, data generated from devices with different
characteristics and located at different positions are embedded into different contexts. This …

In multi-class classification tasks, like human activity recognition, it is often assumed that
classes are separable. In real applications, this assumption becomes strong and generates …

In this paper we will discuss metalearning and how we can go beyond the current classical
learning paradigm. We will first address the importance of inductive biases in the learning …

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 …

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 …

Deep neural networks have revolutionized Machine Learning, completely reshaping several
domains of research in a mere decade. Domains like computer vision, for which deep …