Durée
30h Th, 60h Proj.
Nombre de crédits
Enseignant
Langue(s) de l'unité d'enseignement
Langue anglaise
Organisation et évaluation
Enseignement au deuxième quadrimestre
Horaire
Unités d'enseignement prérequises et corequises
Les unités prérequises ou corequises sont présentées au sein de chaque programme
Contenus de l'unité d'enseignement
In an age where sophisticated algorithms drive innovation, deep learning stands at the forefront, underpinning many breakthroughs in science and engineering. From advancing medical diagnostics with image recognition, to reshaping natural language processing, deep learning has become indispensable across many domains.
In this context, this course offers an immersive exploration of deep neural networks, emphasizing end-to-end model development for tasks such as visual recognition, text and speech understanding, or the design of autonomous intelligent systems. Lectures will delve into the details of neural network architectures, ensuring students not only learn the theoretical underpinnings but also master the practical aspects. Students will learn to implement, train and debug their own neural networks and gain a detailed understanding of cutting-edge research in the field.
Topics to be covered (tentative and subject to change):
- Fundamentals of machine learning
- Multi-layer perceptron
- Automatic differentiation
- Training neural networks
- Convolutional neural networks
- Computer vision
- Attention and transformers
- GPT and large language models
- Graph neural networks
- Uncertainty
- Auto-encoders and variational auto-encoders
- Diffusion models
Acquis d'apprentissage (objectifs d'apprentissage) de l'unité d'enseignement
At the end of the course, the student will have acquired a solid and detailed understanding of the field of deep learning. He/she will have studied both well-established and novel algorithms (in theory and practice) and will also have become familiar with some of the many open research questions and challenges of the field.
Ce cours contribue aux acquis d'apprentissage I.1, I.2, I.3, II.1, II.2, III.1, III.2, III.3, III.4, IV.1, IV.3, IV.4, V.2, VI.1, VI.2, VII.1, VII.2, VII.4, VII.5 du programme d'ingénieur civil en science des données.
Ce cours contribue aux acquis d'apprentissage I.1, I.2, II.1, II.2, III.1, III.2, III.3, III.4, IV.1, IV.8, V.2, VI.1, VI.2, VII.1, VII.2, VII.4, VII.5 du programme d'ingénieur civil électricien.
Ce cours contribue aux acquis d'apprentissage I.1, I.2, II.1, II.2, III.1, III.2, III.3, III.4, IV.1, V.2, VI.1, VI.2, VII.1, VII.2, VII.4, VII.5 du programme d'ingénieur civil en informatique.
Savoirs et compétences prérequis
Programming experience. Probability and statistics.
Following "ELEN0062 Introduction to Machine learning" before taking this class is strongly recommended.
Activités d'apprentissage prévues et méthodes d'enseignement
- Theoretical lectures
- Homeworks
- Programming project
Mode d'enseignement (présentiel, à distance, hybride)
Lectures will taught face-to-face. Projects will be carried out remotely.
Supports de cours, lectures obligatoires ou recommandées
Slides will be made publicly available on GitHub during the semester.
Modalités d'évaluation et critères
Examen(s) en session
Toutes sessions confondues
- En présentiel
évaluation orale
Travail à rendre - rapport
Explications complémentaires:
Examen(s) en session
Toutes sessions confondues
- En présentiel
évaluation orale
Travail à rendre - rapport
Explications complémentaires:
The evaluation is divided into the following units:
- Exam
- Homeworks
- Programming project
Stage(s)
Remarques organisationnelles et modifications principales apportées au cours
The website for the course is https://github.com/glouppe/info8010-deep-learning
Contacts
- Teacher: Prof. Gilles Louppe (g.louppe@uliege.be)