Résultats de recherche

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

Moisson de récompenses pour le centre de recherche NaDI-CeRCLe ces dernières semaines. Les recherches en management des services de trois jeunes doctorants de la Faculté EMCP ont en effet été reconnues par leurs pairs lors d’événements scientifiques internationaux de premier plan : il s’agit de Floriane Goosse, Victor Sluÿters et Florence Nizette. Cet été, nous vous proposons de découvrir leurs parcours et leurs travaux.  

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)

Abstract Detecting semantic code clones in logic programs is a longstanding challenge, due to the lack of a unified definition of semantic similarity and the diversity of syntactic expressions that can represent similar behaviours. This thesis introduces a formal and flexible framework for semantic clone detection based on Constrained Horn Clauses (CHC). The approach considers two predicates as semantic clones if they can be independently transformed, via semantics-preserving program transformations, into a common third predicate. At the core of the method lies anti-unification, a process that computes the most specific generalisation of two predicates by identifying their shared structural patterns. The framework is parametric in regard with the allowed program transformations, the notion of generality, and the so-called quality estimators that steer the anti-unification process. Jury Prof. Wim Vanhoof - University of Namur, BelgiumProf. Katrien Beuls - University of Namur, BelgiumProf. Jean-Marie Jacquet - University of Namur, BelgiumProf. Temur Kutsia - Johannes Kepler University, AustriaProf. Frédéric Mesnard - University of the Reunion, Reunion IslandProf. Paul Van Eecke - Free University of Brussels, Belgium

Abstract In recent decades, the volume of data generated worldwide has grown exponentially, significantly accelerating advancements in machine learning. This explosion of data has led to an increased need for effective data exploration techniques, giving rise to a specialized field known as dimensionality reduction. Dimensionality reduction methods are used to transform high-dimensional data into a low-dimensional space (typically 2D or 3D), so that it can be easily visualized and understood by humans. Algorithms such as Principal Component Analysis (PCA), Multidimensional Scaling (MDS), and t-distributed Stochastic Neighbor Embedding (t-SNE) have become essential tools for visualizing complex datasets. These techniques play a critical role in exploratory data analysis and in interpreting complex models like Convolutional Neural Networks (CNNs). Despite their widespread adoption, dimensionality reduction techniques, particularly non-linear ones, often lack interpretability. This opacity makes it difficult for users to understand the meaning of the visualizations or the rationale behind specific low-dimensional representations. In contrast, the field of supervised machine learning has seen significant progress in explainable AI (XAI), which aims to clarify model decisions, especially in high-stakes scenarios. While many post-hoc explanation tools have been developed to interpret the outputs of supervised models, there is still a notable gap in methods for explaining the results of dimensionality reduction techniques. This research investigates how post-hoc explanation techniques can be integrated into dimensionality reduction algorithms to improve user understanding of the resulting visualizations. Specifically, it explores how interpretability methods originally developed for supervised learning can be adapted to explain the behavior of non-linear dimensionality reduction algorithms. Additionally, this work examines whether the integration of post-hoc explanations can enhance the overall effectiveness of data exploration. As these tools are intended for end-users, we also design and evaluate an interactive system that incorporates explanatory mechanisms. We argue that combining interpretability with interactivity significantly improves users' understanding of embeddings produced by non-linear dimensionality reduction techniques. In this research, we propose enhancements to an existing post-hoc explanation method that adapts LIME for t-SNE. We introduce a globally-local framework for fast and scalable explanations of t-SNE embeddings. Furthermore, we present a completely new approach that adapts saliency map-based explanations to locally interpret non-linear dimensionality reduction results. Lastly, we introduce our interactive tool, Insight-SNE, which integrates our gradient-based explanation method and enables users to explore low-dimensional embeddings through direct interaction with the explanations. Jury Prof. Wim Vanhoof - University of Namur, BelgiumProf. Benoit Frénay - University of Namur, BelgiumProf. Bruno Dumas - University of Namur, BelgiumProf. John Lee - University of Louvain, BelgiumProf. Luis Galarraga - University of Rennes, France

Programme : 17h : Accueil & présentation du film17h15 :  Projection du film Ex machina19h05 : Débat « L’IA a-t-elle une conscience ? » (avec Isabelle Linden & Benoît Frenay)19h45 : finDeux experts prendront part au débat : Benoît Frenay qui apportera un éclairage sur les logiques d’apprentissage des intelligences artificielles actuelles et les limites de leur « autonomie ». Peut-on vraiment parler d’intelligence sans conscience ? Jusqu’où peut aller l’imitation ?Isabelle Linden qui interrogera les fondements mêmes de ce que nous appelons « penser » dans une logique informatique. Peut-on créer une machine consciente ? Ou ne sommes-nous que face à des miroirs de nos propres désirs ? S'inscrire

Chercheur·euses, doctorant·es, artistes, designers, enseignant·es, créatif·ves de tous horizons : c’est une occasion unique de faire sortir vos idées du cadre habituel pour les faire vivre autrement. Objectif de cette première édition : concevoir ensemble une chasse au trésor ludo-pédagogique à Namur, autour de la thématique de la désinformation, destinée aux jeunes de 15 à 18 ans.En pratiqueQuand ? les 1, 2 et/ou 3 juin 2026 (9h–16h), participation flexible (quelques heures, une demi-journée, une journée ou 3 jours)Où ? Le TRAKK à NamurLunch offert par le NADI + café/thé à volonté dans une ambiance collaborativeTout est prévu pour expérimenter, tester, créerInscription : gratuite, mais envoyez un mail à digifactory.asbl@gmail.comUn moment pour croiser les disciplines, sortir des silos…et inventer d’autres manières de raconter, de transmettre et de partager.NB: Pour les doctorant·es, la participation est valorisable dans le parcours doctoral (crédits de formation).OrganisateursJulie Henry, Fanny Boraita, Fanny Barnabé, Benoît Vanderose, Xavier Devroey, Maxime Verbesselt

Une initiative pédagogique originale a été menée à l’Université de Namur durant l’année académique 2024‑2025 dans le cadre du cours Test et Qualité logicielle du master en informatique, orientation software engineering. Cette démarche a conduit à la publication du SNAIL Report 2025, un véritable baromètre des pratiques de développement logiciel en Fédération Wallonie‑Bruxelles.

Dernièrement, et grâce à LUMI, l’un des plus gros supercalculateurs européens, les limites de nos connaissances en matière de membranes lipidiques de cellules ont été repoussées. Une équipe de chercheurs namurois, composée du Professeur Benoît Champagne et des Docteurs Pierre Beaujean et Charlotte Bouquiaux, vient de publier dans la revue Journal of Chemical Information and Modeling. Les résultats de cette étude ouvrent la voie pour de nouvelles approches dans le domaine de la thérapie lipidique membranaire.

Un an après l’obtention d’un financement du Conseil Européen de la Recherche (ERC) pour son projet B-Yond, le Prof Guillaume Berionni vient d’être nommé membre de la prestigieuse société européenne de chimie Chemistry Europe. Cette distinction fait de lui le nouveau représentant pour la Belgique pour une période de 2 ans.

Le Prof Olivier Deparis et le Dr Sébastien Mouchet (Université de Namur, Institut NISM, Département de physique) publient un livre sur le thème de l’optique physique et de la biologie environnementale. Sur les traces des recherches du Prof Jean-Pol Vigneron, ce livre, avant-gardiste selon l’éditeur, ouvre la porte aux applications bio-inspirées dans le monde de l’optique, de l’énergie et de l’environnement. Explications.

Progressivement, des technologies de plus en plus sophistiquées envahissent nos sphères d’activités sans que nous ayons préalablement été consultés en tant que citoyens. Les nouveaux outils numériques, intelligences artificielles ou technologies issues des progrès en neurosciences, qui transforment nos rapports identitaires et sociaux, ne devraient-ils pas faire l’objet de vastes débats démocratiques suffisamment informés ? Cette question est au cœur du projet de «recherche-action» international «Un nouvel humanisme au temps des neurosciences et de l’intelligence artificielle» auquel participe l’UNamur.