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
curriculum [2023/06/22 18:40]
scornet [Scientific Courses, period 2 (January - March)]
curriculum [2023/06/22 18:41] (current)
scornet [Scientific Courses, period 2 (January - March)]
Line 83: Line 83:
 ==== Scientific Courses, period 2 (January - March) ==== ==== Scientific Courses, period 2 (January - March) ====
  
-**INF649 ​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, 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 learningMonte Carloand 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 applicationsWe 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, Lidarintertial unitsodometry …) and the different components ​of navigation: control; obstacle avoidance; localization;​ mapping ​(SLAM) and trajectory planning ​as well as filtering (Kalman filterparticle 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.
curriculum.txt · Last modified: 2023/06/22 18:41 by scornet