Search results

A flurry of awards for the NaDI-CeRCLe research center in recent weeks. The service management research of three young doctoral students from the EMCP Faculty has been recognized by their peers at leading international scientific events: Floriane Goosse, Victor Sluÿters and Florence Nizette. This summer, we invite you to discover their careers and their work.

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, Japan

Can we still speak of democracy when algorithms influence our electoral choices or participate in the drafting of laws? This topic is explored by Aline Nardi, researcher at the Faculty of Law and member of the Namur Digital Institute (NADI).

The Namur Digital Institute (NaDI) is launching a series of original events: "Les Séances du Numérique". Films followed by debates with experts to understand digital challenges and stimulate collective thinking. A project spearheaded by Anthony Simonofski, Anne-Sophie Collard, Benoît Vanderose and Fanny Barnabé.

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, Japan

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, Japan

Researchers, graduate students, artists, designers, teachers, and creatives from all walks of life: this is a unique opportunity to take your ideas beyond the usual framework and bring them to life in a new way. The goal of this first edition: to collaboratively design an educational treasure hunt in Namur, centered on the theme of misinformation, aimed at young people aged 15 to 18.Practical detailsWhen? June 1, 2, and/or 3, 2026 (9 a.m.–4 p.m.), flexible participation (a few hours, half a day, a full day, or all three days)Where? The TRAKK in NamurLunch provided by NADI + unlimited coffee/tea in a collaborativeatmosphere Everything is set up for experimenting, testing, and creatingRegistration: free, but please send an email to digifactory.asbl@gmail.comA chance to bridge disciplines, break out of silos…and invent new ways to tell stories, convey information, and share.Note: For doctoral students, participation counts toward your doctoral program (course credits).

An innovative educational initiative was carried out at the University of Namur during the 2024–2025 academic year as part of the “Software Testing and Quality” course in the Master’s program in Computer Science, with a focus on software engineering. This initiative led to the publication of the SNAIL Report 2025, a comprehensive barometer of software development practices in the Wallonia-Brussels Federation.

On Thursday 29 September 2022, the Vice-Rector for International Relations, the International Relations Service and the Department of Geology received Professor Fakher Jamoussi (Tunisia) as part of the "Tunisia on the move - 2022" project. For more than twenty years, the teams of Professors Johan Yans and Fakher Jamoussi have been weaving scientific, didactic and human collaborations aiming at enhancing the fabulous subsoil of Tunisia.

An international team of researchers, including Prof Frederik De Laender, from the University of Namur, publish in Nature Communications. The editor highlights that the authors use theoretical models and field data to show how eco-evolutionary processes can force species to develop more similar characteristic traits in more species-rich communities to avoid competition. Which goes against what we intuitively perceive.

From 11 to 13 May 2022, a hundred or so scientists and actors from the economic and cultural world gathered at UNamur to discuss the issue of water pollution. The aim? To share and enrich knowledge, but also to alert and inform about its long-term effects on fauna, flora and human beings. Scientific sessions, workshops and a conference for the public were on the programme for these three days.

Increasingly sophisticated technologies are invading our spheres of activity without our prior consultation as citizens. Shouldn't the new digital tools, artificial intelligence or technologies resulting from progress in neuroscience, which are transforming our identity and social relationships, be the subject of broad and sufficiently informed democratic debates? This question is at the heart of the international "research-action" project "A new humanism in the age of neuroscience and artificial intelligence" in which UNamur is participating.