User Tools

Site Tools


curriculum

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
curriculum [2022/03/02 10:56]
scornet [Scientific courses, period 1 (October - December)]
curriculum [2023/06/22 18:41] (current)
scornet [Scientific Courses, period 2 (January - March)]
Line 2: Line 2:
 ==== Detailed curriculum ==== ==== Detailed curriculum ====
  
 +===== 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)
 ===== MASTER 2 ====== ===== MASTER 2 ======
 ==== Pre-training period (September) ====  ==== Pre-training period (September) ==== 
 Choice between: Choice between:
   * MAP630 - Refresher in Statistics : statistical analysis, introduction to Machine Learning techniques (Pierre Latouche, CNRS).   * MAP630 - Refresher in Statistics : statistical analysis, introduction to Machine Learning techniques (Pierre Latouche, CNRS).
-  * INF630 - Refresher in Computer Science : C++ programming,​ basics of 3D modeling, algorithmic ​geometry and computer ​animation (Pooran Memari, CNRS and Damien Rohmer, EP).+  * INF630 - Refresher in Computer Science : Algorithmic ​geometry and character ​animation (Pooran Memari, CNRS and Marie-Paule Cani, EP).
  
  
 ==== Scientific courses, period 1 (October - December) ==== ==== Scientific courses, period 1 (October - December) ====
  
-**MAP/​INF631 - Deep Learning (48h, ECTS), Erwan Scornet (EP)** (contact: erwan.scornet@polytechnique.edu)+**MAP/​INF631 - Deep Learning (48h, 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. ​
  
-**INF633 - Advanced 3D Graphics: Exploring the links between Computer Graphics and AI (24h, 2 ECTS), ​ Marie-Paule Cani (EP), Julien Pettré (Inria), ​Pierre Ecormier ​(EP)** (contact: Marie-Paule.Cani@polytechnique.edu)+**INF633 - Advanced 3D Graphics: Exploring the links between Computer Graphics and AI (24h, 2 ECTS), ​ Marie-Paule Cani (EP), Julien Pettré (Inria), ​Eduardo Alvarado ​(EP)** (contact: Marie-Paule.Cani@polytechnique.edu)
   Computer graphics tackles the creation of 3D contents, from object prototypes to animated scenes. This course will focus on the interactions between Computer Graphics and Artificial Intelligence,​ which recently lead to a number of advances. In particular, we will cover "​Creative AI", ie. how interactive content creation can be enhanced using smart graphical models embedding knowledge, as well as the combination of 3D Graphics, knowledge and learning for the animation and training of possibly autonomous, virtual creatures. ​   Computer graphics tackles the creation of 3D contents, from object prototypes to animated scenes. This course will focus on the interactions between Computer Graphics and Artificial Intelligence,​ which recently lead to a number of advances. In particular, we will cover "​Creative AI", ie. how interactive content creation can be enhanced using smart graphical models embedding knowledge, as well as the combination of 3D Graphics, knowledge and learning for the animation and training of possibly autonomous, virtual creatures. ​
   ​   ​
-**INF632 - Natural Language ​and speech ​Processing : from knowledge modeling to machine learning ​(24h, 2 ECTS), Chloé Clavel (Telecom ParisTech), Fabian Suchanek (Telecom ParisTech) ** (contact: suchanek@telecom-paristech.fr)+**INF632 - Natural Language Processing : Methods and Applications ​(24h, 2 ECTS), Chloé Clavel (Telecom ParisTech), Fabian Suchanek (Telecom ParisTech) ** (contact: suchanek@telecom-paristech.fr)
   During this course, the students will acquire the different methods underlying speech and language processing. The techniques and concepts that will be studied include: ​ part-of-speech tagging, information extraction, knowledge representation,​ dependency parsing, and application of machine learning methods (such as deep learning, hidden markov models) to text classification. ​   During this course, the students will acquire the different methods underlying speech and language processing. The techniques and concepts that will be studied include: ​ part-of-speech tagging, information extraction, knowledge representation,​ dependency parsing, and application of machine learning methods (such as deep learning, hidden markov models) to text classification. ​
    
-**INF631 - Analysis and Deep Learning on Geometric Data (24h, 2 ECTS), Maks Ovsjanikov (EP), Etienne Corman (CNRS) (contact: maks@lix.polytechnique.fr)+**INF631 - Analysis and Deep Learning on Geometric Data (24h, 2 ECTS), Maks Ovsjanikov (EP), Etienne Corman (CNRS)** (contact: maks@lix.polytechnique.fr)
   This course will introduce students to advanced topics in modern geometric data analysis with focus on a) mathematical foundations (discrete differential geometry, mapping, optimization),​ and b) deep learning for best performing methods. We will give an overview of the foundations in shape analysis and processing before moving to modern techniques based on deep learning for solving problems such as shape classification,​ correspondence,​ parametrization,​ etc.   This course will introduce students to advanced topics in modern geometric data analysis with focus on a) mathematical foundations (discrete differential geometry, mapping, optimization),​ and b) deep learning for best performing methods. We will give an overview of the foundations in shape analysis and processing before moving to modern techniques based on deep learning for solving problems such as shape classification,​ correspondence,​ parametrization,​ etc.
-   +      
-    +**INF634 - Computer Vision ​ (24h, 2 ECTS), Vicky Kalogeiton (EP)** (contact: vicky.kalogeiton@polytehcnique.edu)
-**INF634 - Advanced ​Computer Vision ​ (24h, 2 ECTS), Vicky Kalogeiton (EP)** (contact: vicky.kalogeiton@polytehcnique.edu)+
   This course is an introduction to fundamental and advanced topics in computer vision with learning-based approaches,​ ie. Deep Learning. Topics include image and video classification,​ object detection, action recognition,​ optical flow and motion, multi-modal vision systems, annotation signal and applications.   This course is an introduction to fundamental and advanced topics in computer vision with learning-based approaches,​ ie. Deep Learning. Topics include image and video classification,​ object detection, action recognition,​ optical flow and motion, multi-modal vision systems, annotation signal and applications.
  
Line 31: Line 83:
 ==== Scientific Courses, period 2 (January - March) ==== ==== Scientific Courses, period 2 (January - March) ====
  
-**MAP/​INF641 ​Reinforcement Learning ​(48hECTS), ​Odalric-Ambrym Maillard ​(Inria Lille)** (contact: ​odalricambrym.maillard@inria.fr) +**INF657G ​Navigation for Autonomous systems ​(24hECTS), ​David Filliat ​(ENSTA)** (contact: ​david.filliat@ensta-paris.fr) 
-   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.  +   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 - 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 navigateMoreoverenforcing rules and verifying ​that these moving entities stick to their specifications is essential for safetyThis course ​will focus on safe robot navigationintroduce 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 specificationBeyond correctness or robustnesswe are also interested in questions such as explainability ​and fairness, ​that can in turn be specified as formal verification problemsIn 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),  Frederic Landragin (CNRS), Michael Neff (University of California, Davis)** (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.
  
-**INF644 - Virtual/​Augmented Reality & 3D Interactions ​ (24h, 2 ECTS), Anatole Lecuyer (Inria), Fernando Argelaguet Sanz (Inria), Maud Marchal (INSA Rennes), ​Guillaume Moreau (Centrale Nantes), Jean-Marie Normand (Centrale Nantes), Fabien Lotte (Inria)** (contact: Anatole.Lecuyer@inria.fr)+**INF644 - Virtual/​Augmented Reality & 3D Interactions ​ (24h, 2 ECTS), Anatole Lecuyer (Inria Rennes), ​Martin Hachet, Fabien Lotte (Inria ​Bordeaux)** (contact: Anatole.Lecuyer@inria.fr)
   Reconstructing our world or generating virtual ones would be useless without novel ways to navigate and interact with them. This course will present virtual reality systems and the associated methods for navigation and interaction,​ from multi-modal interaction merging visual immersion, sound and haptics systems to brain-computer interfaces.   Reconstructing our world or generating virtual ones would be useless without novel ways to navigate and interact with them. This course will present virtual reality systems and the associated methods for navigation and interaction,​ from multi-modal interaction merging visual immersion, sound and haptics systems to brain-computer interfaces.
   ​   ​
Line 58: 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; Florian Bourgey <​maxime.sangnier@lpsm.paris>​) 
-  * INF538: Refresher in Computer science (two days, in September; Christophe Lino <​christophe.lino@lix.polytechnique.fr>​) 
- 
- 
- 
-=== Period 1 === 
- 
-+ Mandatory scientific courses: 
- 
-  * Machine Learning I (INF554, Michalis Vazirgiannis,​ EP) or Foundations of Machine Learning (MAP553, Erwan Le Pennec, EP) 
- 
-+ 3 courses among: ​ 
- 
-  * Digital representation and analysis of shapes (INF574, Maks Ovsjanikov, Luca Castelli, EP) 
-  * Image Analysis and Computer Vision (INF573, Mathieu Bredif, EP) 
-  * Constraint-based Modeling and Algorithms for Decision Making Problems (INF555, François Fages, Sylvain Soliman, Inria) 
-  * Signal processing (MAP555, Rémi Flamary, EP) 
- 
-+ Mandatory non-scientific courses 
- 
-  * Fundamental of Strategy and Innovation (MIE555) or Marketing and Strategy Introduction (MIE556, Workload ++) 
-  *  Sport 
-  *  Humanities 
-  *  Foreign languages ​ 
- 
-  
-=== Period 2 === 
- 
-4 scientific courses among those below with 
- 
-+ at least one among  
- 
-  * Regression (MAP569, Karim Lounici, EP) 
-  * Real-time AI in Video Games: decisive & collaborative actions (INF584A) ​ 
-  * Advanced Machine Learning and autonomous agents (INF581) 
-  * Statistics in action (MAP566) 
- 
-+ and at least one among  
- 
-   * Algorithmic geometry: from theory to applications (INF562, Luca Castelli, EP)  
-   * Computer animation (INF585, Damien Rohmer, EP) 
-   * Image synthesis: Theory and practice (INF584, Tamy Boubekeur, Telecom ParisTech) 
- 
- 
-+ Mandatory non-scientific courses 
- 
- 
-  *  Entrepreneurship for sustainability (MIE568) or Managing sustainable innovation (MIE565) ​ 
-  *  Sport  
-  *  Humanities ​ 
-  *  Foreign languages ​ 
- 
-=== Period 3 === 
- 
-MAP/INF590 - Internship (4 to 6 months) 
curriculum.1646214962.txt.gz · Last modified: 2022/03/02 10:56 by scornet