Description

Deep Learning becomes more and more popular with algorithms based on these techniques performing very well for a variety of problems and scientific communities. The course has been designed to provide an introduction to deep learning techniques, including neural networks, computer vision, natural image processing and reinforcement learning. In particular, it will cover the fundamental aspects and the recent developments in deep learning: Feedforward networks and their optimisation and regularisation, representation learning and siamese networks, Generative Adversarial Networks and transfer learning, recurrent networks and Long Short Term Memory units, transformers, deep Reinforcement Learning.

Learning objectives
The course aims to introduce students to the design of deep learning methodologies both in theory and practice. We expect that by the end of the course, the students will:
• have knowledge of state-of-the-art deep learning techniques
• have a deeper understanding of deep learning methods
• have practical experience with deep learning frameworks

General Information

Program and Classrooms
24/10 13:30-16:45 Introduction (Auditorium 1 Michelin, Eiffel)
31/10 13:30-16:45 Optimization (Amphi e.070, (theatre) Bouygues)
07/11 13:30-16:45 Generative Adversarial Networks (Auditorium 1 Michelin, Eiffel)
14/11 13:30-16:45 Introduction to Computer Vision (Auditorium 3 Michelin, Eiffel)
05/12 13:30-16:45 Self-Supervision (Auditorium 3 Michelin, Eiffel)
12/12 13:45-16:45 Reinforcement Learning (Auditorium 3 Michelin, Eiffel)
09/01 13:45-17:00 Natural Language Processing
16/01 13:45-17:00 Guest & Poster session

Announcements

Announcements are not public for this course.
Staff Office Hours
NameOffice Hours
Maria Vakalopoulou
When?
Where?
Vincent Lepetit
When?
Where?
David Picard
When?
Where?
Doriand Petit
When?
Where?
Théo Moutakanni
When?
Where?
Asma BRAZI
When?
Where?
Nabil
When?
Where?
Sofiène Boutaj
When?
Where?