curriculum
Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
|
curriculum [2022/05/31 18:46] scornet [MASTER 1] |
curriculum [2022/09/01 11:11] cani [Scientific Courses, period 2 (January - March)] |
||
|---|---|---|---|
| Line 33: | Line 33: | ||
| Reinforcement learning aims at finding at each step of a process the best action to take in order to minimize some regret function. This course will introduce the general notions of reinforcement learning and will present several online algorithms that can be used in real-time to take actions. The specificity and the performance of the different algorithms will be discussed in detail. | Reinforcement learning aims at finding at each step of a process the best action to take in order to minimize some regret function. This course will introduce the general notions of reinforcement learning and will present several online algorithms that can be used in real-time to take actions. The specificity and the performance of the different algorithms will be discussed in detail. | ||
| - | **INF641 - Robot motion planning, verification and control of hybrid systems (24h, 2 ECTS), David Filliat (ENSTA), Eric Goubault (EP), Sylvie Putot (EP)** (contact: david.filliat@ensta-paristech.fr) | + | **INF641 - Introduction to the verification of neural networks (24h, 2 ECTS), Eric Goubault (EP), Sylvie Putot (EP)** (contact: sylvie.putot@polytechnique.edu) |
| - | Drones and robots need to build maps of their environments to plan their motion and navigate. Moreover, enforcing rules and verifying that these moving entities stick to their specifications is essential for safety. This course will focus on safe robot navigation, introduce map building techniques, present motion planning methods and give an introduction to control and verification of the resulting hybrid systems. | + | Neural networks are widely used in numerous applications including safety-critical ones such as control and planning for autonomous systems. A central question is how to verify that they are correct with respect to some specification. Beyond correctness or robustness, we are also interested in questions such as explainability and fairness, that can in turn be specified as formal verification problems. In this course, we will see how formal methods approaches introduced in the context of program verification can be leveraged to address the verification of neural networks. |
| **INF642 - Socio-emotional embodied conversational agents (24h, 2 ECTS), Catherine Pelachaud (CNRS - ISIR), Chloé Clavel (TelecomParistech) ** (contact: catherine.pelachaud@upmc.fr) | **INF642 - Socio-emotional embodied conversational agents (24h, 2 ECTS), Catherine Pelachaud (CNRS - ISIR), Chloé Clavel (TelecomParistech) ** (contact: catherine.pelachaud@upmc.fr) | ||
| Line 98: | Line 98: | ||
| 2 scientific courses among | 2 scientific courses among | ||
| - | * Regression (MAP569, Karim Lounici, EP -- with pre-requisit in mathematical fundations of ML) | + | * Regression (MAP569, Karim Lounici, EP, difficult math course, with pre-requisit in mathematical fundations of ML, see also the book (2018) Foundations of Machine Learning; please contact the teacher before the beginning of the course) |
| * Statistics in action (MAP566, Julien Chiquet, EP & Agro Paris Tech) | * Statistics in action (MAP566, Julien Chiquet, EP & Agro Paris Tech) | ||
| * Real-time AI in Video Games: decisive & collaborative actions (INF584A, David Bilemdjian, Chaire Ubisoft) | * Real-time AI in Video Games: decisive & collaborative actions (INF584A, David Bilemdjian, Chaire Ubisoft) | ||
curriculum.txt · Last modified: 2023/06/22 18:41 by scornet
Page Tools
