curriculum
Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
|
curriculum [2023/04/21 09:47] cani [Detailed curriculum] |
curriculum [2023/06/22 18:41] (current) scornet [Scientific Courses, period 2 (January - March)] |
||
|---|---|---|---|
| Line 65: | Line 65: | ||
| ==== Scientific courses, period 1 (October - December) ==== | ==== Scientific courses, period 1 (October - December) ==== | ||
| - | **MAP/INF631 - Deep Learning (48h, 5 ECTS), Erwan Scornet (EP)** (contact: erwan.scornet@polytechnique.edu) | + | **MAP/INF631 - Deep Learning (48h, 4 ECTS), Erwan Scornet (EP)** (contact: erwan.scornet@polytechnique.edu) |
| Deep Learning is one key element of modern data science. This course will explore several instances of Deep Neural Networks, each one being specifically adapted to solve a particular learning task (classification, image recognition, text mining, dimensionality reduction). An introduction to current research topics on neural network will be presented during the last part of the course. | Deep Learning is one key element of modern data science. This course will explore several instances of Deep Neural Networks, each one being specifically adapted to solve a particular learning task (classification, image recognition, text mining, dimensionality reduction). An introduction to current research topics on neural network will be presented during the last part of the course. | ||
| Line 83: | Line 83: | ||
| ==== Scientific Courses, period 2 (January - March) ==== | ==== Scientific Courses, period 2 (January - March) ==== | ||
| - | **MAP/INF641 - Deep Reinforcement Learning (24h, 2 ECTS), Jesse Read** (contact: jesse.read@polytechnique.edu) | + | **INF657G - Navigation for Autonomous systems (24h, 2 ECTS), David Filliat (ENSTA)** (contact: david.filliat@ensta-paris.fr) |
| - | Reinforcement learning (RL) is of increasing relevance today in science and industry, for developing autonomous agents in areas where dynamic decision making and adaptation is required; including games, energy systems, recommendation engines, finance, logistics, and auto-tuning the parameters of large and powerful computer models (for NLP, computer vision, etc). This course will take a deep look at the foundations of RL, the main learning paradigms (temporal-difference learning, Monte Carlo, and policy gradients methods), their modern state-of-the-art variants, and how they can be enhanced and deployed with deep-learning architectures to tackle problems at a scale found in the real world. We will also take a look at specialized topics such inverse reinforcement learning. | + | Drones and robots must create maps of their surroundings to plan their movement and navigate. This course presents the robotic platforms and the most common sensors (vision, Lidar, intertial units, odometry …) and the different components of navigation: control; obstacle avoidance; localization; mapping (SLAM) and trajectory planning as well as filtering (Kalman filter, particle filtering, etc.) and optimization techniques used in these fields. |
| + | | ||
| **INF641 - Introduction to the verification of neural networks (24h, 2 ECTS), Eric Goubault (EP), Sylvie Putot (EP)** (contact: sylvie.putot@polytechnique.edu) | **INF641 - Introduction to the verification of neural networks (24h, 2 ECTS), Eric Goubault (EP), Sylvie Putot (EP)** (contact: sylvie.putot@polytechnique.edu) | ||
| 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. | 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. | ||
| - | **INF657G - Navigation for Autonomous systems (24h, 2 ECTS), David Filliat (ENSTA)** (contact: david.filliat@ensta-paris.fr) | ||
| - | Drones and robots must create maps of their surroundings to plan their movement and navigate. This course presents the robotic platforms and the most common sensors (vision, Lidar, intertial units, odometry …) and the different components of navigation: control; obstacle avoidance; localization; mapping (SLAM) and trajectory planning as well as filtering (Kalman filter, particle filtering, etc.) and optimization techniques used in these fields. | ||
| - | |||
| **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) | ||
| Many interactive systems, from virtual companions to online retailing, rely on embodied conversational agents. These agents need to reach a good level of communication skills to conduct a conversation with humans and be acceptable and trustworthy by humans. This course will introduce non-verbal behavior models, present models for multimodal dialog, opinion detection and voice quality, explain how to model the agent's emotions and their evolution over time, and present methods for enhancing naturalism with expressive gaze and gestures, realistic animation. | Many interactive systems, from virtual companions to online retailing, rely on embodied conversational agents. These agents need to reach a good level of communication skills to conduct a conversation with humans and be acceptable and trustworthy by humans. This course will introduce non-verbal behavior models, present models for multimodal dialog, opinion detection and voice quality, explain how to model the agent's emotions and their evolution over time, and present methods for enhancing naturalism with expressive gaze and gestures, realistic animation. | ||
| + | **INF649 - Deep Reinforcement Learning (24h, 2 ECTS), Jesse Read** (contact: jesse.read@polytechnique.edu) | ||
| + | Reinforcement learning (RL) is of increasing relevance today, including in games, complex energy systems, recommendation engines, finance, logistics, and for auto-tuning the parameters of other learning frameworks. This course assumes familiarity with the foundations of RL and its main paradigms (temporal-difference learning, Monte Carlo, and policy-gradient methods). We will explore them further, and study modern state-of-the-art variants (such as proximal policy optimization), with a focus on developing RL solutions with deep neural architectures suited to modern applications. We will also take a look at specialized topics such inverse reinforcement learning. | ||
| + | |||
| **INF643 - Soft robots: simulation, fabrication, and control (24h, 2 ECTS), Christian Duriez (Inria Lille), Sylvain Lefebvre (Inria Nancy) ** (contact: christian.duriez@inria.fr) | **INF643 - Soft robots: simulation, fabrication, and control (24h, 2 ECTS), Christian Duriez (Inria Lille), Sylvain Lefebvre (Inria Nancy) ** (contact: christian.duriez@inria.fr) | ||
| Soft robotics is a promising novel field, bringing more robustness in robots design and for all tasks involving close interactions with humans, from help to disable people to medical robot. This course will give an introduction to recent advances in soft robotics, including topological optimization for additive fabrication, modeling and control techniques for robots, and will present recent applications in medicine, industry and art. | Soft robotics is a promising novel field, bringing more robustness in robots design and for all tasks involving close interactions with humans, from help to disable people to medical robot. This course will give an introduction to recent advances in soft robotics, including topological optimization for additive fabrication, modeling and control techniques for robots, and will present recent applications in medicine, industry and art. | ||
| Line 112: | Line 112: | ||
| - | ==== Final project (April to September - 30 ECTS) ==== | + | ==== Final project (April to September - 32 ECTS) ==== |
| MAP/INF690 - Internship: 5 to 6 months project, either in the R&D department of a company or in a research lab. | MAP/INF690 - Internship: 5 to 6 months project, either in the R&D department of a company or in a research lab. | ||
| - | ===== MASTER 1 ===== | ||
| - | |||
| - | All courses are 36h and will represent 4 ECTS. | ||
| - | |||
| - | * MAP538: Refresher in statistics (two days, in September; Maxime Sangnier <maxime.sangnier@lpsm.paris>) | ||
| - | * INF538: Refresher in Computer science (two days, in September; XXXX Ask Amal Dev Parrakat?) | ||
| - | |||
| - | === Period 1 === | ||
| - | |||
| - | + Scientific courses: | ||
| - | |||
| - | Mandatory: | ||
| - | * Digital representation and analysis of shapes (INF574, Mathieu Desbrun, Pooran Memari, EP & Inria) | ||
| - | |||
| - | 1 course among: | ||
| - | * Machine Learning I (INF554, Michalis Vazirgiannis, EP) | ||
| - | * Foundations of Machine Learning (MAP553, Erwan Le Pennec, EP) | ||
| - | |||
| - | 2 courses among: | ||
| - | * Image Analysis and Computer Vision (INF573, Mathieu Brédif, EP & IGN) | ||
| - | * Constraint-based Modeling and Algorithms for Decision Making Problems (INF555, François Fages, EP & Inria) | ||
| - | * Signal processing (MAP555, Rémi Flamary, EP) | ||
| - | * Topological data analysis (INF556, Steve Oudot, EP & Inria) | ||
| - | |||
| - | + Mandatory non-scientific courses | ||
| - | |||
| - | * Fundamental of Strategy and Innovation (MIE555) or Marketing and Strategy Introduction (MIE556, Workload ++) | ||
| - | * Sport | ||
| - | * Humanities | ||
| - | * Foreign languages | ||
| - | |||
| - | |||
| - | === Period 2 === | ||
| - | |||
| - | Mandatory course: | ||
| - | * Advanced Machine Learning and autonomous agents (INF581, Jesse Read, EP) | ||
| - | * Computer animation (INF585, Damien Rohmer, EP) | ||
| - | |||
| - | 2 scientific courses among | ||
| - | * 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) | ||
| - | * Real-time AI in Video Games: decisive & collaborative actions (INF584A, David Bilemdjian, Chaire Ubisoft) | ||
| - | * Algorithmic geometry: from theory to applications (INF562, Luca Castelli, EP) | ||
| - | * Image synthesis: Theory and practice (INF584, Tamy Boubekeur, Telecom ParisTech) | ||
| - | |||
| - | + Mandatory non-scientific courses | ||
| - | * Entrepreneurship for sustainability (MIE568, wednesday morning), or Managing sustainable innovation (MIE565, friday afternoon) | ||
| - | * Sport | ||
| - | * Humanities | ||
| - | * Foreign languages | ||
| - | |||
| - | === Period 3 === | ||
| - | MAP/INF590 - Internship (4 to 6 months) | ||
curriculum.1682063226.txt.gz · Last modified: 2023/04/21 09:47 by cani
Page Tools
