Search results

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 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

Something for everyone 09:30 | Welcome ceremony for new students11:00 | Back-to-school celebration at Saint-Aubain Cathedral (Place Saint-Aubain - 5000 Namur), followed by student welcome by the Cercles. Read more

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 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

Trust of traditional political institutions and elected representatives, rise of authoritarian logics, definition of public services... Democracy today seems to be going through a turbulent zone. What role does the university play in this context? To shed light on this question, we interviewed four researchers from different disciplines: educationalist Sephora Boucenna, philosopher Louis Carré, political scientist Vincent Jacquet and legal scholar Aline Nardi. Their contrasting views sketch out the contours of an issue that is more topical than ever: thinking about and defending the link between university and democracy.

Florentin Rochet, a professor of computer security at the University of Namur, specializes in applied cryptography and secure communications. Against the backdrop of rapid advances in artificial intelligence and open-source solutions, he shares his analysis of the current situation and offers his outlook for the future. 

On Wednesday, May 6, 2026, His Majesty the King visited UNamur. In collaboration with Henallux and IMEP, students from the Faculty of Education (FaSEF) led several interactive workshops focused on key issues in education. On the agenda: discussions with His Majesty the King on topics such as inclusion, the diversification of learning, the development of critical thinking in the age of artificial intelligence, challenges facing the education sector, and sustainable development.

September 15, 2025 A program for all09h00 | Welcome at Pedro Arrupe (Rue de Bruxelles, 67 - 5000 Namur).11h00 | Back-to-school celebration at Saint-Aubain Cathedral (Place Saint-Aubain - 5000 Namur) then welcome students by the Cercles. Daily prices Tuesday, September 16, 2025For Block 1 (Local I02)* - Welcome session08H30: Presentation of the Dean/Vice-Dean (Anthony Cleve - Marie-Ange Remiche)09H00: Presentation of the IS (Cédric Aerts)09H20: Presentation of the pedagogical coordinator (Fanny Boraita)09H40: Presentation of the academic advisor (Géraldine Grandjean)For students in the first 60 credits of the bachelor's degree (only first-time students*)10H40 (Local I02): passport to the "mathematics" baccalaureate(Florence Henry)Attendance at these sessions is compulsory.For UES** and new Master's students (Local I33) - Welcome session14H00: Presentation of the Dean/Vice-Dean (Anthony Cleve - Marie-Ange Remiche)14H30: Presentation of the IS (Cédric Aerts)14H50: Presentation of the pedagogical coordinator (Fanny Boraita)15H10: Presentation of the academic advisor (Géraldine Grandjean)15H30: Presentation of CSLabs (Hugo Raskin)Wednesday, September 17, 2025For Block 1 (Local I02)*<13H00: Passport "lire et comprendre un texte universitaire" (Alexandre Libioul)Attendance at this session is compulsoryFor all students: Classes start (see schedule)Permanences PAE17/09, 10h40-11h40 for NON-primo-arrivants from bloc1: Configuration PAE (salle académique)17/09, 09h00-10h00 for bacheliers from bloc2 and 3: Configuration PAE (salle académique)18/09, 09h00-10h00 for masters: Configuration PAE (salle académique)* First-time students : Students enrolled for the first time in a computer science study program at UNamur, whether they are coming from secondary school, a high school, another university or enrolled in staggered-schedule courses. ** UES: Unités d'enseignement supplémentaires au master (année passerelle) Staggered timetable courses Bachelor and Master 60Saturday, September 13, 2025 - Classes startFor Primo-arrivant students (Block 1 and UES):08:30: Breakfast welcome (coffee, pastries) in the faculty hall.09h00: Presentations by the Vice-Dean, Madame Marie-Ange REMICHE, the Academic Advisor, Madame Géraldine GRANDJEAN, the IT Correspondent, Monsieur Cédric AERTS and the Secretary, Madame Benjamine LURQUIN. Auditorium I02 (first floor of the Faculty of Computer Science). Attendance is compulsory. The welcome session presentation will be posted on the BVE afterwards.10:00 am: Start of classes for all students. Master's specialization in IT and innovation: business analysis and it governance For students concerned by prerequisite coursesSaturday, September 13, 2025 at 9:00 am, seminar I22 on the 2nd floor of the Faculty.For all new studentsCourses start on Friday, October 17 and Saturday, October 18, 2024 at the Academic Hall on the 4th floor of the Faculty of Computer Science, from 8:30 am. And before school starts? In addition to preparatory courses, UNamur offers newcomer students the opportunity to discover their Faculty and the campus, and to take part in a services forum during 2 integration days.Put all the advantages on your side, take part in the preparatory courses!For future medical students, the preparatory courses enable you to prepare for the entrance exam, and for all other students, to discover university teaching by revising the subjects essential to your future training.Exclusively designed for students completing their secondary education (newcomers), these preparatory courses, programmed between mid-August and early September, are tailored to each university program.Learn more about the schedules for the various sessions and register for the preparatory courses...  NEW! To help you make the most of your first year at the University, take part in our integration days!Friday afternoon, September 12 - reserved for newcomers, free, registration requiredTour of your Faculty and campusBarbecue and evening partyYou must register for both activities, even if you are enrolled in the preparatory courses! Registration link: https://www.billetweb.fr/journees-dintegration-unamur-2025.Saturday September 13 from 12pm to 4pm - open to all - free, free accessServices forum: presentation of student services (sports, culture, commitment, social cell, ...), project kots and activities organized on campus...

September 15, 2025 A program for all09h00 | Welcome at Pedro Arrupe (Rue de Bruxelles, 67 - 5000 Namur).11h00 | Back-to-school celebration at Saint-Aubain Cathedral (Place Saint-Aubain - 5000 Namur) then welcome students by the Cercles. MSFE (Master of Specialization in Teacher Training) September 16, 2025Welcome session: from 18h10 to 19h10, at B&LC, salle MEUSE, rue Godefroid, 5 - 5000 Namur. All those interested in the program, in the process of registering or already registered are welcome to attend. The MSFE is a 60-credit program, offered on a staggered schedule, mainly on Tuesdays and Thursdays (in the evening) and Saturdays all day. This master's degree of specialization is aimed in particular at future (or current) instructors at Hautes Écoles and Écoles Supérieures des Arts, in charge of UEs linked to didactics, pedagogy and training to and through practice in the master's programs in teaching sections 1, 2, 3, 4 and 5, who will need to have this diploma within six years of first appointment to a position for which this master's degree is required. It will also be of interest, as part of their professional development, to all teacher trainers in continuing education, whether they carry out their duties within inter-network or network continuing education organizations, or as freelancers.All information on the program Schedule: available at https://horaires.unamur.be, Student/Faculty of Education/MSFE tab Contact : gaelle.chapelle@unamur.be and secretariat.fasef@unamur.be > CAPAES September 16, 2025Reception session: from 7:10pm to 10:10pm, at B&LC, salle SAMBRE, rue Godefroid, 5 - 5000 Namur. The CAPAES is organized in staggered hours on Tuesdays and Thursdays (in the evening). The CAPAES is intended only for teachers working in a haute-école or in social promotion higher education for whom obtaining a pedagogical title appropriate to higher education is a necessity. All information on the program Schedule: available at https://horaires.unamur.be, Student/Faculty of Education/CAPAES tab Contact : gaelle.chapelle@unamur.be and secretariat.fasef@unamur.be > MAPEMASS (Master's degree in professional support) September 16, 2025Welcome session: from 6:10 pm to 9:10 pm, room L33 (Faculté de Philosophie et Lettres building,1 rue Joseph Grafé, 5000 - Namur).All those interested in the program, in the process of enrolling or already enrolled, are welcome to attend.MAPEMASS is a 60-credit program, offered on a staggered schedule, mainly on Tuesdays and Thursdays (in the evening) and Saturdays all day.The Master of Specialization in Support for Professionals in Education, Management, Health and Social Action (MAPEMASS) offers original training and pursues the ambition of offering trainers, team leaders, consultants, HR managers, etc. training in supporting teams and the professionals who make them up. All information on the programSchedule: available on https://horaires.unamur.be, Student/Faculty of Education/MAPEMASS tabContact : sephora.boucenna@unamur.be and secretariat.fasef@unamur.be Masters in Teaching (sections 4 and 5) September 15, 2025from 12:40pm to 2pm, room BN141. And before school starts? In addition to preparatory courses, UNamur offers newcomer students the opportunity to discover their Faculty and the campus, and to take part in a services forum during 2 integration days.Put all the advantages on your side, take part in the preparatory courses!For future medical students, the preparatory courses enable you to prepare for the entrance exam, and for all other students, to discover university teaching by revising the subjects essential to your future training.Exclusively designed for students completing their secondary education (newcomers), these preparatory courses, programmed between mid-August and early September, are tailored to each university program.Learn more about the schedules for the various sessions and register for the preparatory courses...  NEW! To help you make the most of your first year at the University, take part in our integration days!Friday afternoon, September 12 - reserved for newcomers, free, registration requiredTour of your Faculty and campusBarbecue and evening partyYou must register for both activities, even if you are enrolled in the preparatory courses! Registration link: https://www.billetweb.fr/journees-dintegration-unamur-2025.Saturday September 13 from 12pm to 4pm - open to all - free, free accessServices forum: presentation of student services (sports, culture, commitment, social cell, ...), project kots and activities organized on campus...