Search results

An unusual piece of research recently mobilized teams from UNamur's Biology Department. Genetic analyses carried out by the Environmental and Evolutionary Biology Research Unit (URBE) were able to confirm the protected status of a herd of wild mouflons based in Gesves, and thus highlight the importance of saving them.

The NaDI-CeRCLe research center has distinguished itself brilliantly on the international scene in recent weeks. Three young researchers from the EMCP Faculty have received prestigious recognition at leading international events for their research in service management: they are Floriane Goosse, Victor Sluÿters and Florence Nizette. This summer, let's discover the work of these PhD students and their significant contributions to the advancement of knowledge and practice in this field.

A lifelong video game enthusiast, Fanny Barnabé, a researcher at the CRIDS research center (Namur Digital Institute) and lecturer at the University of Namur, explores behind the scenes of a major cultural phenomenon: video game streaming on Twitch. Between humor, irony and toxic discourse, she deciphers the issues at stake in a digital space in the throes of change.

High-Sensitivity Birefringence Mapping Using Near-Circularly Polarized Light I will describe several techniques for mapping a two-dimensional birefringence distribution, which can be classified according to the optical schemes and principles of work:Illumination geometry (transmitted light/reflected light)Image acquisition (sequential acquisition/simultaneous acquisition)Polarization control (electrically controlled variable retardance/mechanical rotation).This classification facilitates a comparative analysis of the capabilities and limitations in these methods for birefringence characterization. Polychromatic polarizing microscopy (PPM) provides unique capabilities to alternative methods. It leverages vector interference to generate vivid, full-spectrum colors at extremely low retardances, down to < 10 nm. PPM is a significant departure from conventional polarizing microscopes that rely on Newton interference, which requires retardances above 400 nm for color formation. Furthermore, PPM's color output directly reflects the orientation of the birefringent material, a feature absent in conventional microscopy where color is solely determined by retardance.Joint seminar of ILEE & NISM!The seminar is open to external people too, no need to register. More info

From 2020 to 2025, as part of her doctoral thesis in history, researcher Julie Duchêne conducted a ground-breaking investigation blending history and biology to trace the cohabitation between humans and wolves in Wallonia and Luxembourg, from the 18th to the early 20th century. Thanks to an innovative interdisciplinary approach, including DNA analysis of naturalized 19th-century specimens, her work sheds light on the mechanisms that led to the local extinction of the species. This research was made possible thanks to the support of numerous scientific and cultural partners.

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

Deadlines Opening of abstract submissions and registrations: September 15, 2025Deadline to submit indicative title and summary: November 30, 2025Deadline for final abstract submissions: May 1, 2026Early bird registration deadline: March 1, 2026 More information on the website

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

This summer's third and final focus on the NaDI-CeRCLe research center, which has gained international recognition in recent weeks thanks to awards won by three young researchers in service management. Following on from Floriane Goosse and Victor Sluÿters, we invite you to discover the work of Florence Nizette, a young researcher working on Artificial Intelligence technologies.

A project submitted by Professor Frédéric Silvestre's Laboratoire de Physiologie Évolutive et Adaptative (LEAP) at the University of Namur has been ranked among the top 6 research projects funded by the FNRS and the Fonds de recherche du Québec (FRQ) for scientific collaboration between Wallonia and Quebec. The aim? To understand the impact of human activities on St. Lawrence Estuary (SLE) belugas, using interdisciplinary approaches to help improve conservation strategies for this threatened species..

A team of American researchers, with the help of Frédérik De Laender, professor in the Department of Biology at UNamur, has just published in the prestigious journal Nature. Their study describes how changing stream temperatures and human introductions of fish can alter river biodiversity in the USA.

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