Résultats de recherche

Titre de la première présentation - Concepts introductifs et applications récentes en sciences socialesTitre de la deuxième présentation - NLP, LLM et IA - Exploration d'outils avancés pour les économistes et les spécialistes en sciences sociales Restez informés ! Pour rester informé des détails des prochains séminaires, merci de vous inscrire à notre liste de diffusion ci-dessous. Je minscris à la liste de diffusion

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

BNAIC/BeNeLearn 2025 will be held at the University of Namur under the auspices of the Belgian-Dutch Association for Artificial Intelligence (BNVKI) and the Dutch Research School for Information and Knowledge Systems (SIKS). The conference aims at presenting an overview of state-of-the-art research in artificial intelligence and machine learning in Belgium, The Netherlands, and Luxembourg. More information and registration

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

Professeur en sécurité informatique à l’Université de Namur, Florentin Rochet a fait de la cryptographie appliquée et des communications sécurisées son domaine d’expertise. Entre progression galopante de l’intelligence artificielle et solutions open source, il partage son analyse de la situation actuelle et livre ses perspectives pour l’avenir. 

Publicités, réseaux sociaux, radio, télévision, presse écrite, plateformes numériques … les moyens de communication sont multiples et prennent aujourd’hui une place très importante dans notre quotidien. Mais comment ces médias fonctionnent-ils ? Comment les informations circulent-elles dans la société actuelle ? Et comment peut-on communiquer de façon à la fois efficace et créative, mais aussi critique et responsable ? En devenant des professionnels de la communication et du journalisme au service des médias, des entreprises et des associations, vous apprenez à décoder ces messages et à vous faire entendre dans cette abondance d’information.

Comment les États et les citoyens peuvent-ils agir face à la menace climatique ? Pourquoi l’extrême droite gagne-t-elle les élections ? Quels sont les modes de résolution des conflits armés ? L’Union européenne a-t-elle un avenir après le Brexit ? Les sciences politiques fournissent des clés d’analyse pour étudier ces enjeux.   Le bachelier en sciences politiques est une formation de pointe pour celles et ceux qui souhaitent comprendre les transformations des sociétés contemporaines et devenir acteurs dans les ONG, les gouvernements, les entreprises, les institutions européennes et internationales. 

Intensification des rythmes de travail, déséquilibre vie pro-perso, contrôle accru des performances… le monde du travail traverse des mutations profondes. Comment, dans ce contexte, permettre aux individus de s’engager et de s’épanouir durablement dans leur activité professionnelle ? Un nouveau projet de recherche ARC baptisé « SUSCARE » propose une solution originale : remettre le concept de care au cœur des pratiques organisationnelles.

Nouveaux marchés, concurrence accrue, progrès technologiques, mais aussi enjeux écologiques, énergétiques, politiques et de qualité de vie… Les défis à relever sont nombreux et les besoins sans cesse croissants. Abordez les problématiques économiques et sociales sous un regard nouveau et sensible à la responsabilité sociétale et éthique, à l’interdisciplinarité, à la dimension internationale et aux défis de la transition pour façonner l’avenir durable de notre société. Bienvenue à la Faculté Economie Management Communication sciencesPo (EMCP) !

Invited speakers: Manuel GARCÍA-SANTANA (Universitat Pompeu Fabra) and Eric VERHOOGEN (Columbia University)Audience: PhD studentsCall for papers: PhD students and postdocs are invited to submit a paper by April 15, 2026. Applicants will be notified by May 15, 2026. Accepted contributions will be presented in a poster session, with a subset selected for seminar-style presentations. Your paper can be sent to this address : nathan.jespere@unamur.be

Dans le cadre des Inforums et des séminaires CyberExcellence, nous aurons le plaisir d’accueillir le Dr. Ryan Wails (Georgetown University), qui nous parlera de cyber-sécurité. Vous trouverez l’abstract de sa présentation ainsi que sa bio ci-dessous.Pas d'inscription nécessaire.Nous espérons vous retrouver nombreux·ses à cet événement !On the Interplay of Modern Traffic Analysis and Internet Censorship & Circumvention TechniquesIn this talk, I will review the current state of real-world Internet censorship and some tools that network users employ to circumvent censorship. Then, I'll take a prospective view about how censors might incorporate modern ML-based traffic analysis techniques to block users, motivating the need for stronger circumvention tools. Finally, I'll discuss our new internet censorship evasion technique called Unidentified Protocol Generation (published at USENIX Security 2025, which is able to evade detection by state-of-the-art traffic analysis.Author bio: Ryan Wails is a Postdoc a Georgetown University researching network privacy and security. He has been doing his PhD while working at the US Naval Research Laboratory. This lab is known for originating the Tor network, and creating the PETs research community which is now among the top international research communities in computer security. Ryan is a core contributor of the Tor project and has published in top conferences on Networking simulators, privacy attacks, privacy-preserving measurements, path selection algorithms, censorship circumvention, and website fingerprinting. He received several international disctinctions, including Best papers in top conferences and award recognitions at community events for his contributions.

Le 13 mai dernier se tenaient les présentations des projets de génie logiciel (projet MDL de son petit nom) devant le jury composé des coachs et des clients externes venus pour l’occasion. À travers les 7 projets présentés cette année, les étudiants ont pu montrer leurs réalisations, mais aussi expliquer comment ils ont interagi avec leurs clients pour mener à bien leurs développements.