Search results

The workshop provides a forum for the discussion of new research directions and applications in Artificial Life, Evolutionary Computation and in related fields, where different disciplines and research areas could effectively meet. It was first held in 2007 in Sampieri (Ragusa), as the incorporation of two separate workshops (WIVA and GSICE).

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

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

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

Our keynote speakers for 2026 are Professor Roosmarijn Vandenbroucke (Ghent University) and Professor Nelly Litvak (Eindhoven University of Technology). More information on the "Women in Science" website

Abstract Deep learning has become a central part of everyday life, and has given us powerful digital tools such as machine translators, voice assistants, and large language models. The Deaf communities, however, benefit verylittle from this progress. Sign languages are full natural languages, but they have no widely used written form, so the large text corpora and pretrained models that support these tools for spoken languages have no direct equivalent. As a result, sign language processing is held back by two related problems: a persistent shortage of annotated data, and a lack of tools to analyze the languages themselves.This thesis focuses on one component of the sign language processing pipeline that has received comparatively little attention: sign language segmentation, the temporal partitioning of a continuous signing video into individual sign units. Segmentation sits between raw video and almost every symbolic task built on top of it, yet it remains poorly understood. The goal of this work is twofold: to advance the segmentation task itself, and to turn sign language processing research into tools that are usable by the Deaf community, with French Belgian Sign Language (LSFB) as the main setting.The central contribution of this thesis is a set of segmentation models. We first study approaches based on recurrent neural networks, and show that their main difficulty lies in the modeling of the transitions between signs, the brief ambiguous movements that separate one sign from the next and that are easily confused with the signs themselves. This insight motivates the Hydra framework, a new approach that detects each sign as a whole unit rather than deciding, frame by frame, whether a sign is being produced. Concretely, instead of classifying every frame, the model predicts the distance from each frame to the nearest sign boundaries, which makes it less sensitive to the ambiguous regions and improves consistently over prior methods. Around this core, we present further contributions: a sign language-to-text dictionary that recognizes signs from an ordinary webcam, supporting work on isolated sign recognition, and a collaborative platform that gathers new sign data as a side effect of everyday use. Together, these contributions narrow the gap between sign language processing research and the people whose language it concerns. Jury Prof. Benoit Frénay - University of Namur, BelgiumProf. Anthony Cleve - University of Namur, BelgiumProf. Katrien Beuls - University of Namur, BelgiumProf. Barbara Hammer - Bielefeld University, GermanyProf. Michèle Gouiffès - Paris-Saclay University, FranceDr. Mathieu De Coster - Ghent University, Belgium I am registering to attend Pierre Poitier's thesis defense

What's on the agenda for everyone 9:00 a.m. | Welcome reception at the Pedro Arrupe, Rue de Bruxelles 67, 5000 Namur9:30 a.m. | Ceremony at the Espace Pedro Arrupe 11:00 a.m. | Back-to-School Celebration at Saint-Loup Church—to be confirmed, Rue du Collège, 5000 Namur—followed by a welcome for students by the student clubs.Other specific activities for this day are available on each faculty’s webpage. More information on the Back-to-School page

Take part in our open morning Given the works in the rue de Bruxelles and the renovation of part of the University parking lots, we invite you to use public transport whenever possible (train or bus) to reach Namur. UNamur boasts an ideal location, in the heart of the city just a five-minute walk from the TEC and SNCB train stations.If you're coming by car, take a look at the parking map provided. Look forward to seeing you on Saturday, June 29!

Save the date! On Saturday June 28, 2025, from 1pm to 5pm, UNamur once again opens its doors to you before the summer vacations.At the programProfessors, assistants, students and staff members look forward to welcoming you to answer all your questions about your future studies;share with you their experience of university life and its many opportunities for fulfillment;guide you through your final practical steps: registration, preparatory courses, finding accommodation, financial aid and more.Forthcoming informationThe afternoon's detailed program will be available some ten days before the event. Find out more about the open house

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

In practice Who are open courses for?Open courses are open to all, although they are primarily aimed at secondary school students to help them take that first step in exploring higher education.What is the schedule for open courses?Courses are open from February 27 to Wednesday, March 5, 2025, from 08:30 to 16:30.To find out the precise timetable and location of each course, please visit the Info études service (Rue de Bruxelles, 85 5000 Namur), 15 minutes before the start of the course.The provisional program is available 15 days before the start of open courses.How to meet a guidance counselorYou have the opportunity to meet a guidance counselor at the guidance workshop scheduled for Tuesday, March 4, 2025, from 1:30 to 4:00 pm.The aim of this workshop is to help you think about the guidance process, gain a better understanding of the higher education landscape and define the main markers in the process of clarifying your project (educational and professional).Our advisor is also available by appointment for a one-to-one meeting throughout the week of open courses and outside of it.Do you have to register to take part?Access to open courses is without prior registration.To participate in the orientation workshop, however, online registration is mandatory and will be available some ten days before the start of the open courses.Who organizes the open courses?Open courses are organized by Info études, the service that provides information on all matters relating to choice of studies, prerequisites, reorientation, gateways, course curricula, job opportunities, additional training, recognition of prior learning... or any general questions about university life in Namur. Find out more about open courses