Résultats de recherche

SynopsisOver recent years, the development of agent-based models has allowed researchers to advance their understanding of naturally occurring collective behaviours. Swarm robotics, a field studying the design of decentralised robot swarms, has emerged following the replication of some collective behaviours in artificial groups of robots. The first part of this thesis provides novel techniques for the aggregation of heterogeneous swarms. First, we enhance an existing controller for an aggregation problem on two sites through the use of informed robots. We show that our simplified approach offers a wider range of operating conditions and a greater flexibility. Second, we provide a new method for the aggregation of robot swarms with adaptive random walks. We separately study cue-based aggregation with a swarm of robots only sensing private information and neighbour-based aggregation with a swarm of robots sensing social information. We show that a trade-off can be obtained with a heterogeneous swarm composed of the two robot types, forming a dense cluster near the minimum of an environmental cue. Private and social information also play a key role in the evolution of biological processes inside animal groups. Dispersal, the movement of an animal from site of birth to site of reproduction, is strongly affected by the acquisition and the use of information. Since experimental research is often difficult to conduct while accounting for multiple information sources and environmental variability, the use of agent-based models offer an opportunity to study the evolution of dispersal and its associated costs linked to private and social information in a controlled setting. The second part of this thesis provides an agent-based model of dispersal including the acquisition of information and its associated costs. Throughout three case studies, we observe the evolution of genes linked to the acquisition of information and the obtained dispersal strategies in different scenarios. Jury members Prof. Wim Vanhoof, Président, Université de Namur, BelgiqueProf. Elio Tuci, Secrétaire, Université de Namur, BelgiqueProf. Timoteo Carletti, Membre interne, Université de Namur, Belgique Prof. Eliseo Ferrante, Membre externe, Vrije Universiteit Amsterdam, Pays-BasProf. Mauro Birattari, Membre externe, ULB, Belgique Prof. Andreagiovanni Reina, Membre externe, Universität Konstanz, Allemagne 

The workshop will feature:A keynote presentation on public value and AI implementation at VRT.Sessions on discoverability, user agency, and explainability.Discussions on regulation, including perspectives on the AI Act and transparency in media.An interactive session showcasing AI-driven prototypes.The event will also highlight our project’s latest findings. Join us for a day of thought-provoking discussions, knowledge exchange, and networking opportunities!Would you like to attend? Places are limited and will be allocated on a first-come, first-served basis, so register as soon as possible. Registration will close on April 11, 2025. More information here

Pour Bruno Dumas, l’informatique s’inscrit dans les principes de la psychologie appliquée L’intelligence artificielle (IA) s’immisce dans nos vies professionnelles comme dans nos vies privées. Elle nous séduit comme elle nous inquiète. À l’échelle mondiale, elle est au cœur d’importants enjeux stratégiques, sociétaux ou économiques, débattus encore mi-février 2025, lors du sommet mondial de l’IA à Paris. Mais comment ne pas la subir en tant qu’utilisateur ? Comment avoir accès à cette nécessaire transparence de son fonctionnement ? En plaçant son prisme de recherche du côté de l’utilisateur, Bruno Dumas est en quelque sorte « un psychologue de l’informatique ». Expert en interaction humain-machine, co-président de l’Institut NaDI (Namur Digital Institut), il défend l'idée d'une utilisation raisonnée et éclairée des technologies émergentes. 

Un ordinateur peut-il apprendre une langue comme le fait un enfant ? Une étude récente publiée dans la revue de référence Computational Linguistics par les professeurs Katrien Beuls (Université de Namur) et Paul Van Eecke (AI-lab, Vrije Universiteit Brussel) apporte un nouvel éclairage sur cette question. Les chercheurs plaident pour une révision fondamentale de la manière dont l'intelligence artificielle acquiert et traite le langage. 

Abstract Deep learning has become an extremely important technology in numerous domains such as computer vision, natural language processing, and autonomous systems. As neural networks grow in size and complexity to meet the demands of these applications, the cost of designing and training efficient models continues to rise in computation and energy consumption. Neural Architecture Search (NAS) has emerged as a promising solution to automate the design of performant neural networks. However, conventional NAS methods often require evaluating thousands of architectures, making them extremely resource-intensive and environmentally costly.This thesis introduces a novel, energy-aware NAS pipeline that operates at the intersection of Software Engineering and Machine Learning. We present CNNGen, a domain-specific generator for convolutional architectures, combined with performance and energy predictors to drastically reduce the number of architectures that need full training. These predictors are integrated into a multi-objective genetic algorithm (NSGA-II), enabling an efficient search for architectures that balance accuracy and energy consumption.Our approach explores a variety of prediction strategies, including sequence-based models, image-based representations, and deep metric learning, to estimate model quality from partial or symbolic representations. We validate our framework across three benchmark datasets, CIFAR-10, CIFAR-100, and Fashion-MNIST, demonstrating that it can produce results comparable to state-of-the-art architectures with significantly lower computational cost. By reducing the environmental footprint of NAS while maintaining high performance, this work contributes to the growing field of Green AI and highlights the value of predictive modelling in scalable and sustainable deep learning workflows. Jury Prof. Wim Vanhoof - University of Namur, BelgiumProf. Gilles Perrouin - University of Namur, BelgiumProf. Benoit Frénay - University of Namur, BelgiumProf. Pierre-Yves Schobbens - University of Namur, BelgiumProf. Clément Quinton - University of Lille, FranceProf. Paul Temple- University of Rennes, FranceProf. Schin’ichi Satoh - National Institute of Informatics, Japon

Abstract Plastic pollution has emerged as a pervasive environmental threat, with micro- and nanoplastics (MPs and NPs) accumulating across ecosystems and organisms, including humans. Their ability to adsorb and transport contaminants raises critical concerns for both environmental and public health.This thesis investigates the developmental neurotoxicity of MPs and NPs in zebrafish (Danio rerio), emphasizing the influence of particle size and mixture toxicity. NPs were shown to cross the embryonic chorion, disrupt physiological functions, and induce anxiety-like behaviour, whereas MPs mainly altered gene expression related to neurodevelopment. When co-exposed with methylmercury (MeHg), NPs enhanced MeHg accumulation in the brain and sensory organs, exacerbating its neurotoxic effects. Notably, the mixture induced severe hypoactivity, impaired lipid metabolism and neurotransmission, and increased mortality.These findings highlight the critical need to assess plastic particle toxicity not only in isolation but also in environmentally relevant mixtures. NPs, due to their small size and high reactivity, may act as vectors for toxicants like MeHg, amplifying their effects during sensitive developmental stages. Jury Prof. Frédéric SILVESTRE (UNamur), PrésidentProf. Patrick KESTEMONT (UNamur), SecrétaireDr Valérie CORNET (UNamur)Prof. Eli THORÉ (UNamur)Prof. Jérôme CACHOT (Université de Bordeaux)Dr Krishna DAS (Université de Liège)

Près de 10 000 kilomètres séparent la Belgique du Japon, un pays qui fascine, notamment pour sa culture riche et pleine de contrastes. Les chercheurs de l’UNamur entretiennent des liens étroits avec plusieurs institutions nipponnes, notamment dans les domaines de l’informatique, des mathématiques ou encore du jeu vidéo. Coup de projecteur sur quelques-unes de ces collaborations.

Le Namur Digital Institute (NaDI) lance un cycle de rendez-vous originaux : « Les Séances du Numérique ». Des films suivis de débats avec des experts et expertes pour comprendre les défis du numérique et stimuler la réflexion collective. Un projet porté par Anthony Simonofski, Anne-Sophie Collard, Benoît Vanderose et Fanny Barnabé.