Search results

Professor Elio Tuci has just been awarded Research Credit funding from the FNRS. The naXys institute specializes in the analysis of complex systems, whether in astronomy and dynamic cosmology, mathematical biology, optimization in optics, economic complexity or the study of the stability and robustness of these systems. The institute is structured around 6 research axes: Space, Bio, Optics, Eco, Robust and Robotics.

The workshop will feature:A keynote presentation on public value and AI implementation at VRT.Sessions on discoverability, user agency, and explainability.Discussions on regulation, including perspectives on the AI Act and transparency in media.An interactive session showingcasing AI-driven prototypes.The event will also highlight our project's latest findings. Join us for a day of thought-provoking discussions, knowledge exchange, and networking opportunities!Would you like to attend? Places are limited and will be allocated on a first-come, first-served basis, so register as soon as possible. Registration will close on April 11, 2025. More information here

This thesis presents a novel approach to address the challenges of deploying and managing Network Functions Virtualization (NFV) in resource-constrained and multi-domain environments. The proposed solution leverages a Raspberry Pi clusterbased approach for NFV deployment in resource-constrained environments, combined with a deployable Sidecar VNF (S-VNF) coordinator for multi-domain NFV orchestration.The thesis demonstrates the feasibility of integrating NFV into edge computing environments by successfully deploying and managing Network Services (NSs) on a Raspberry Pi cluster. The S-VNF coordinator facilitates efficient cross-cloud NFV deployment and management while ensuring security and interoperability.While the obtained deployment and scaling delays in the testbed setup were significant due to the bare-metal deployment process used, the proposed solution remains valuable in environments where service maintenance time is a critical factor.By automating deployment and scaling, organizations can minimize the impact of service maintenance time, improve customer satisfaction, and enhance system resilience. Moreover, the solution enables NFV to be deployed effectively in edge environments, providing benefits such as reduced latency and improved network performance.Overall, this thesis contributes to the advancement of NFV by providing innovative solutions for deployment and management in challenging environments. The proposed framework has the potential to enable the widespread adoption of NFV and drive the development of new network services.Directed by Prof. Laurent SCHUMACHER and Prof. Sokchenda SRENG.In front of a jury composed of:Prof. Wim VANHOOF, President, University of NamurProf. Laurent SCHUMACHER, Co-Promoter, University of NamurProf. Sokchenda SRENG, Co-Promoter, ITC Graduate School (Cambodia)Prof. Florentin ROCHET, Internal Member, University of NamurProf. Johann MARQUEZ-BARJA, External Member, University of AntwerpProf. Bruno QUOITIN, External Member, University of MonsProf. Raveth HIN, External Member, ITC Graduate School (Cambodia)You are cordially invited to a drink, which will follow the public defense.For good organization, please give your answer by Thursday March 20 by means of this link.Contact: Daelman Isabelle - isabelle.daelman@unamur.be

This is great recognition for the excellence of the research carried out at the University of Namur: the Faculty of Informatics has been asked to join the prestigious Informatics Europe network, which brings together the most dynamic departments and faculties of Informatics across Europe.

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

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

Registration form Name First name E-mail address Will attend the reception following the defense Yes ( optional ) No ( optional ) Need a parking sticker Yes ( optional ) No ( optional ) Would like a certificate for defense assistance Yes ( optional ) No ( optional ) In order to process your request, you must complete all fields marked "optional". When you submit this form, the completed data will be transmitted to UNamur and used to process your request. Learn more about your data protection and your rights

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

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

Registration form Name First name E-mail address Will attend the reception following the defense Yes ( optional ) No ( optional ) Need a parking sticker Yes ( optional ) No ( optional ) Would like a certificate for defense assistance Yes ( optional ) No ( optional ) In order to process your request, you must complete all fields marked "optional". When you submit this form, the completed data will be transmitted to UNamur and used to process your request. Learn more about your data protection and your rights

While women are still in the minority in technical and scientific fields, confidence and passion have enabled some to overcome stereotypes and structural barriers. Women physicists and computer scientists are leading the way for those who cherish the bench and the screen, the numbers, and the machines.