The program

This course will give an overview of the topics of study of the field of Natural Language Processing.
It will take a problem-centric approach, introducing increasingly complex problems, starting from basic building blocks like language modeling, tagging and parsing; and progressing towards complex problems like opinion mining, machine translation, question & answering and dialogue. While important historical methods will be mentioned (and studied if still relevant), a focus will be on current state-of-the-art involving many times recent advances in training neural networks and novel architectures.

Computer vision is an interdisciplinary field with the goal of enabling automatical processing and understanding of digital images. These images can be captured by video cameras, radars, satellites
or even very specialised sensors such as the ones used for medical purposes. This course covers both theoretical and practical aspects of computer vision. It has been designed to provide an introduction to computer vision, including fundamentals on image processing, computational photography, multiview geometry, stereo, tracking, segmentation and object detection. It will expose students to a number of real-world applications that are important to our daily life. The course will be focusing only on classical computer vision techniques, presenting a detailed overview of classical vision methods, while it does not cover deep learning-based methods.

Reinforcement Learning (RL) methods are at the intersection of several fields such as machine learning, probability theory, control theory, or game theory. They study fundamental tradeoffs between exploitation and exploration in order to optimize a future reward in an unknown environment. Recently, they were successfully applied to many applications such as complex games (Go or Atari), robot control, and selection of experts, leading in many cases to super-human performances in those contexts. This class will cover the necessary tools (from a theoretical and practical point of view) to understand how such a breakthrough was possible.

Deep learning methods are now state of the art in many machine learning tasks, leading to impressive results. Nevertheless, they are still poorly understood, neural networks are still difficult to train,
and the results are black-boxes missing explanations. Given the societal impact of machine learning techniques today (used as assistance in medicine, hiring process, and bank loans…), it is crucial to make their decisions explainable or to offer guarantees. Besides, real world problems usually do not fit the standard assumptions or frameworks of the most famous academic work (data quantity and quality, expert knowledge availability…). This course aims at providing insights and tools to address these practical aspects, based on mathematical concepts.

Networks (or graphs) have become ubiquitous as data from diverse disciplines can naturally be mapped to graph structures. Social networks, such as academic collaboration networks and interaction networks over online social networking applications are used to represent and model social ties among individuals. Information networks, including the hyperlink structure of the Web and blog networks, have become crucial mediums for information dissemination, offering an effective way to represent content and navigate through it. A plethora of technological networks, including the Internet, power grids, telephone networks and road networks are an important part of everyday life. The problem of extracting meaningful information from large-scale graph data in an  efficient and effective way has become crucial and challenging with several important applications. Towards this end, graph mining and analysis methods constitute prominent tools. The goal of this course is to present
recent and state-of-the-art methods and algorithms for analyzing, mining and learning large-scale graph data, as well as their practical applications in various domains (e.g., the web, social networks,
recommender systems).

Medical imaging technologies provide unparalleled means to study the structure and function of the human body in vivo. Interpretation of medical images is difficult due to the need to take into account three-dimensional, time-varying information from multiple types of medical images. Artificial intelligence (AI) holds great promise for assisting in the interpretation and medical imaging is one of the areas where AI is expected to lead to the most important successes. In the past years, deep learning technologies have led to impressive advances in medical image processing and interpretation.
This course covers both theoretical and practical aspects of deep learning for medical imaging. It covers the main tasks involved in medical image analysis (classification, segmentation, registration,
generative models…) for which state-of-the-art deep learning techniques are presented, alongside some more traditional image processing and machine learning approaches. Examples of different
types of medical imaging applications (brain, cardiac…) will also be provided.

The ensemble methods are popular machine learning techniques that are powerful when one wants to deal with both classification and regression prediction problems. The idea is to build a global prediction model by combining the strengths of a set of simpler base models. The random Forests approach is an example that falls into this category by the aggregation of a collection of decision trees.

This course aims to study the fundamental notions and concepts of tree-based methods and ensemble learning. Mainly, we will introduce several methods, such as Classification And Regression Trees (CART), boosting trees, Random Forests, …etc. Furthermore, we want to investigate and discuss some recent challenges of interpretability and regularization through different approaches [Strobl et al., 2007, 2008]. Moreover, the different approaches will be applied to practical cases involving real data throughout the course.

Multi-agent systems (MAS) are currently widely used, especially for complex applications requiring interaction between several entities. More specifically, they are used in applications where it is necessary to solve problems in a distributed manner (data processing) or in the design of distributed systems in which each component has some degree of autonomy (control of processes). Some examples of applications are trading agents, drones, smart grids. This course will begin with an introduction to the notion of agent and multi-agent systems. It will present the concepts that will lead to an understanding of what an agent is and how it can be built. Then, we will address a classical problem of SMAs, namely, how to model and simulate a situation through the concept of agents.
The idea is to give a basis for understanding how agent-based simulations can be used as a tool for understanding human societies or complex problems and situations. Besides, we will discuss how agents can communicate and interact to solve problems, and more specifically, to make noncentralized decisions. For this, we will rely on negotiation protocols based on argumentation theory, a process of constructing and evaluating arguments (positive and negative reasons/evidence) to resolve conflicts.

The aim of this course is twofold. First, we present the main principles concerning decision under uncertainty, and we focus on the use of graphical models when making decision under uncertainty.
In this framework, we show how probabilistic computations can be performed efficiently, and that learning such graphical model (structure and/or parameters) can be based on data. We study in
particular dynamic Bayesian networks, which allow probabilistic reasoning while incorporating time.
Second, we consider principles of game theory and show how such theory can model and analyse decision in situation where uncertain and strategic interactions are involved.

Maintenance is important in engineering systems. In this course, we focus on the optimal planning of maintenance for complex systems. Different maintenance strategies are introduced with a focus on the performance indicators used to quantify their performances and optimization models used to obtain optimal planning. The students are supposed to learn fundamental theoretical results as well as some tools to help them apply the theoretical methods in practical.

Planning in AI focuses on automatically generating sequences of actions that must be performed in order to reach a predefined goal. Actions are represented by operators transforming the states, generally expressed via propositional logic. Several problems in industry or robotics can be formulated as planning problems. Different AI techniques and algorithms are used to solve planning problems.
In classical planning, an agent has perfect knowledge of the states and the effects of the actions, which are deterministic. The relaxation of these assumptions leads to numerous extensions using solving techniques based on diverse AI tools like heuristic search or Markov processes.

In this course, we will introduce the formulation of a planning problem and present the different AI techniques and algorithms for solving it,

Artificial Intelligence aims to solve problems automatically. In particular, Deep Learning allows reaching performances that are often greater than human performances. However, in some application areas, users want to understand why an algorithm proposes a certain decision. This is especially true for human-centered domains, such as medicine and security, or for those that are affected by laws offering a right to explanation (banking sector). For these reasons, the field of XAI (eXplainable Artificial Intelligence) has become very important in recent years, even though the issue has been around for several decades.
This module aims to introduce you to the tools that have emerged from recent or older research and that help to understand the most opaque models, and to familiarize you with interpretability and explainability issues. At the end of this course, the student will have acquired a general view of the XIA domain and its problems.