In Reinforcement Learning (RL), an agent learns how to act in an unknown environment in order to maximize its reward in the long run. In recent years, the use of neural networks has led to breakthroughs, e.g., in scalability. However, there are still gaps in our understanding of how to best employ neural networks in RL. In this thesis, we improve t...
L’estimation du rendement agricole joue un rôle crucial dans la poursuite des objectifs de développement durable des Nations Unies, représentant ainsi un outil essentiel dans la prise de décisions concernant les systèmes d’approvisionnement. Dans ce travail, nous nous intéressons à la prédiction du rendement du Pennisetum glaucum, aussi connu comme...
In the era of artificial intelligence, there has been a growing consensus that solutions to complex science and engineering problems require novel methodologies that can integrate interpretable physics-based modeling approaches with machine learning techniques, from stochastic optimization to deep neural networks. This thesis aims to develop new me...
L’analyse de données est un terme très générique et touche une variété d’analyses possibles, incluant, par exemple, l’analyse décisionnelle (BI) ou l’analyse statistique, dont fait partie l’analyse prédictive. Dans le cadre de l’analyse prédictive, la construction et l’usage de modèles prédictifs, réalisés à l’aide de techniques d’intelligence arti...
Federated Learning (FL) allows clients to collaboratively train a model while preserving data privacy. Despite its benefits, FL is vulnerable to poisoning attacks. This thesis addresses malicious model detection in FL systems for IoT networks. We provide a literature review of recent detection techniques and propose a Secure Layered Adaptation and ...
This thesis addresses the challenge of evaluating candidate logical formulas, with a specific focus on axioms, by synergistically combining machine learning with symbolic reasoning. This innovative approach facilitates the automatic discovery of axioms, primarily in the evaluation phase of generated candidate axioms. The research aims to solve the ...
Recent years have seen a renewed interest in the potential of analogy detection and analogical inference, with successful applications in Machine Learning (ML) to the retrieval and generation of images, of text, and structured data such as knowledge graphs, but also the detection of relations between and within images, texts, and structured data. W...
Nous vivons dans un monde hyperconnecté. À présent, la majorité des objets qui nous entourentéchangent des données soit entre-eux soit avec un serveur. Ces échanges produisent alors de l’activitéréseau. C’est l’étude de cette activité réseau qui nous intéresse ici et sur laquelle porte ce mémoire. Eneffet, tous les messages et donc le trafic réseau...
Measurements are essential to operate and manage computer networks, as they are critical to analyze performance and establish diagnosis. In particular, per-flow monitoring consists in computing metrics that characterize the individual data streams traversing the network. To develop relevant traffic representations, operators need to select suitable...
The study of human behavior is a broad and interdisciplinary field. A variety of research methods has been employed in order to gain insights into the complexities of human actions. The process of identifying and classifying specific activities or actions that individuals perform based on data collected from sensors is a rapidly evolving field that...
