News : (reload for fresher news...)
- TD3 added
- Links to hand in TD1 and TD2 added (password communicated on the mailing-list)
- Register to the mailing-list! as the link to the course online will be given there
- The course will take place online via Microsoft Teams The previous course (January-March 2020) can be found there; the new course will follow more or less the same lines, though not exactly.
The webpage for the new course (2021) is not completely finished; materials from last year and not updated yet are preceded by "".
General information about the course: presentation slides
Teaching team :
Most lectures: Guillaume Charpiat
Practical sessions: Wenzhuo Liu and Nilo Schwencke (incl. materials by Victor Berger)
all announcements (last-minute changes, rooms, projects, etc.) will be made on a dedicated mailing-list; to subscribe, visit this link:
and click on subscribe / s'abonner, or replace /info/ with /subscribe/ in the URL.
Make sure that you do receive an confirmation email; if not, try subscribing with another email address, or contact me.
Auditors (auditeurs libres) are welcome; just subscribe to the mailing-list as well.
Location : online. The course will take place via Microsoft Teams. You can either install the client on your computer (available for Windows/Mac/Linux; this way provides more features), or follow the course via a browser (in which case, better use Chrome). The link to attend the course will be given on the mailing-list above. Do not hesitate to register, even at the last minute.
Schedule : January-March 2021, most often on Tuesday mornings, 9h - 12h15 (3 hours with a 15 minute break), online
(note that the schedule is irregular):
January 26th : Small or noisy data: forms of weak supervision → Practical session on active learning →Lesson summary
February 2nd, 9th, 16th : no course! but 2 sessions the following week:
Monday February 22nd (9h-12h15 as well) : guest talk/course by Olivier Teytaud (Facebook FAIR Paris) about Deep Reinforcement Learning / Evolutionary Deep Computer Vision / Derivative-free Optimization
February 23d : Modeling: deep learning and physics (exploiting known invariances, priors or physical properties), by Michele Alessandro Bucci (LRI, TAU team) and Lionel Mathelin (LIMSI, Paris-Sud) → Practical session on learning dynamical systems →2019's course on similar topics
March 2nd : Generative models (GAN, VAE and Normalizing Flows) + Auto-ML / Auto-DeepLearning (guest talk from Isabelle Guyon's group) → Practical session on generative models
March 9th : Guarantees? Neural Tangent Kernel, generalization and formal proofs