Search results

Democratic Transformations - TRANSDEMThese seminars will focus on how current institutional, economic, environmental and migratory tensions are transforming and challenging the way our democratic regimes function.

More info to come."Methods "seminarsThe Methods Seminar is a series of seminars organized at the University of Namur with the aim of fostering interdisciplinary collaboration and knowledge exchange. All seminars take place in a hybrid format.This seminar series focuses on advanced methodological approaches, particularly in the fields of natural language processing (NLP), artificial intelligence (AI), video and image analysis, and multimodal analysis.To stay informed about details of upcoming seminars, please subscribe to our mailing list below. I subscribe to the "Methods" mailing list

Victimization and identity: the post-heroic society More info to come All TRANSDEM seminars

Humans have always been fascinated by space: they scan the sky and try to understand it. Over time, technological advances provide new observations. These help to improve existing scientific theories while posing new questions.PAF 45€ - Papers and lunch included20€ without lunchFree registration for under-25s and PhD students (with free lunch included for UNamur PhD students).Closing date for registrations 11/03/2026. I want to register

For the past fifteen years or so, participatory and deliberative democracy mechanisms have been multiplying: participatory budgets, popular consultations, citizens' panels, and so on. Vincent Jacquet, a political scientist and coordinator of the European research project Citizen Impact (ERC project, European Research Council), studies the impact of these devices from the point of view of governors and citizens.

Omalius is the magazine of the University of Namur. A quarterly that highlights UNamur's research, its experts, educational innovations and topical issues. Discover the July 2025 issue.

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

The ISALA NOVA project, initiated by UMONS and UNamur and supported by the Sakura Fund of the Foundation for Future Generations, aims to sustainably transform universities in terms of gender equality.

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

Find out more about our social, political and communication sciences programs Image Studies in Information and Communication See content Image Studies at Sciences Po See content PhD It's also possible to continue your training with a PhD in a research unit or center. Registrations for PhDs are open all year round. Find all the information on the PhD registration procedure on the registration department pages. Find out more about the Department of Social, Political and Communication Sciences SVG .cls-1 { fill: #323232; stroke-width: 0px; } Home See content SVG .cls-1 { fill: #323232; stroke-width: 0px; } Research in social, political and communication sciences See content SVG .cls-1 { fill: #323232; stroke-width: 0px; } Organization See content

Hepatocellular carcinoma is the most common primary liver cancer. Unfortunately, this tumor still has a high mortality rate due to the lack of effective treatments for its most advanced or poorly localized forms. As part of a partnership with the CHU UCL Namur - site de Godinne and with the support of Roche Belgium, researchers in the Department of Biomedical Sciences are trying to understand why liver tumor cells are so resistant to treatment, and to identify therapeutic alternatives to better target them.

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