Search results

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.

In an ever-changing world, where health, environmental and societal crises are intertwined, it is becoming imperative to rethink health in a global and interconnected approach. It was against this backdrop that the Faculty of Medicine at the University of Namur inaugurated its new "One Health" teaching unit (UE) on Thursday February 06, 2025, in the presence of Minister Yves Coppieters. This initiative, offered to all UNamur undergraduates, aims to train tomorrow's healthcare professionals in a systemic vision, where human, animal and environmental health are considered as one and the same reality.

Thomas Balligand, now a lecturer at UNamur, combines his passion for basic research with teaching in histology and cytology. After a diverse background in internal medicine and research, notably at Harvard, he is dedicated to training the next generation of scientists while pursuing his work on nanobodies and their potential in immunotherapy. His desire to awaken scientific curiosity in his students illuminates his new role at the university..

Since September 2023, Marc Hennequart, Professor of Biochemistry and Cell Biology at UNamur, has been conducting groundbreaking research into pancreatic cancer. His team, based at the Faculty of Medicine and the Institut Narilis, studies the early stages of oncogenesis (the process of transforming a normal cell into a cancerous one) to better understand the metabolic changes behind this particularly aggressive cancer.

On 13 December 2023, Charlotte Beaudart, a new academic at the University of Namur Faculty of Medicine, will be awarded a prize at the annual ceremony for Belgian scientific research in support of her innovative research on the subject of ageing.

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 public defense will be followed by a reception.Registration required. I want to register

One of the major concerns with the disease caused by Covid-19 is its severe course, which causes many problems that can lead to hospital overload. Early detection of whether or not a person is at risk of developing a severe form of the disease is therefore crucial to optimise patient care and hospital resource management. This is one of the objectives of the study carried out by QUALIblood, a UNamur spin-off, in collaboration with the Department of Pharmacy and many other industrial and hospital partners. Exploration of a cutting-edge technology at the service of health.

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 public defense will be followed by a reception.Registration required. I want to register