Résultats de recherche

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. 

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 Constraint 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 La défense publique (en anglais) sera suivie d'une réception.Inscription obligatoire. Je m'inscris

Le Ten-years Most Influential Paper award vient d’être attribué trois membres de la Faculté d’informatique de l’UNamur : Xavier Devroey, Gilles Perrouin et Maxime Cordy. Ce prix récompense le papier publié dix ans auparavant et dont l’impact sur la communauté de recherche a été le plus important. Il a été remis lors de la 18ème édition de l’International Working Conference on Variability Modelling of Software-Intensive Systems (VAMOS ’24) qui s’est déroulée début février à Berne en Suisse.

L’espace est devenu le lieu d’importants enjeux économiques et stratégiques. Membre de l’Alliance européenne UNIVERSEH, l’UNamur explore cette thématique spatiale dans ses différents départements, de la physique à la géologie, en passant par les mathématiques, l’informatique ou la philosophie. Sans oublier de s’adresser au grand public, que les étoiles font toujours rêver...

Gilles Perrouin vient de recevoir le prix pour l’article le plus influent à la conférence SPLC2024.  Ce prix vient souligner une fructueuse ligne de recherche sur le test de lignes de produits logiciels, déjà primée en février 2024.

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 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 La défense publique sera suivie d'une réception.Inscription obligatoire. Je m'inscris

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 La défense publique sera suivie d'une réception.Inscription obligatoire. Je m'inscris