The objective of this course is to present the basics of machine learning (the different types of contexts/tasks/applications), to understand how the main machine learning methods work, and to give the experimental methodological principles for setting up implementing these methods. The goal is to master the different tasks of machine learning, to understand the differences between the methods and their operating principle and to know how to set up an experimental protocol to test and compare these methods on real data sets. The topics covered are:

• Parametric and non-parametric, generative or discriminant classifiers (Gaussian estimation, Parzen estimator, k nearest neighbors, linear separator (perceptron, SVM))
• Hierarchical classifiers (decision trees)
• Neural networks (MLP)
• The selection of models

The objective of this teaching unit is to introduce the issue of the Web of data both from a historical and technical point of view. These are the technologies of the Semantic Web that make it possible to implement the fundamental principles of this Web of data. This is accompanied by a stack of standards issued by the World Wide Web Consortium (W3C) that this course offers to understand both theoretically and practically. The primary objective of this course is to enable students to acquire knowledge of the operation of the Semantic Web and its architectural principles. This is essential for a good understanding of today's Web given the growing role played by Semantic Web technologies. The secondary objective is to train in the standards of the Semantic Web in order in particular to achieve a concrete and mastered understanding of the notion of ontology and their ability to implement reasoning and deductions from new data. The targeted skills are:

• Understand the concept of Web of data and know the architectural principles of the Semantic Web.
• Master the representation languages adapted to the publication of linked data on the Web (RDF model).
• Master the main aspects of the SPARQL query language which allows the querying and modification of (linked) data through the Web.
• Understand the notion of ontology and the languages used to write them (RDFS, OWL, SKOS).

The objective of this teaching unit is to learn about graphic interface design with Web technologies. It aims to train in the use of HTML / CSS technologies for the creation of Web interfaces, with an emphasis on modern techniques of responsive web design. At the end of this course, students should be able to design multi-media adaptive graphical interfaces, that is to say that are functional on all types of screens (mobile, tablet, computers, etc.). This course does not cover concepts of ergonomics or graphics, but focuses on the technical mastery of dedicated tools. The targeted skills are:

• Master HTML5 for structuring web documents.
• Master the key principles of CSS for the formatting and visual and functional rendering of these pages.
• Master the fundamental techniques of responsive web design (flexible layout, flexible media, media queries, etc...).

The objective of this teaching unit is to present the theoretical and practical tools allowing the processing of random signals, in particular on aspects related to signal filtering. It is a question of mastering the classic approaches for such treatments. The targeted skills are:

• Theoretical deepening of signal processing tools.
• Putting into practice the methods seen in class.

The objective of this teaching unit is to know how to organize teamwork around a development project using AI:

• Know and implement the principles of team management (cycles, agility, etc.)
• Master common project management tools (diagrams, dashboards, version tracking, etc.)

The objective of this teaching unit is to present the management of processes and their communication under Linux: fork, signals, files and pipes, IPC, sockets. It is about knowing how to create a process and controlling its life cycle, and knowing, knowing how to analyze and implement the different types of communication between processes.

The objective of this teaching unit is the presentation of best practices for designing a mobile application, in the case of Android with the Kotlin language: MVVM, injection, tests. It's about knowing how to make an Android application in Kotlin by following the official recommendations for good architecture (MVVM), knowing how to use injection for dependency inversion, and knowing how to create unit tests, integration, and end to end.

The objective of this teaching unit is to design professional documents (CV and cover letter) consistent with a professional objective and to prepare for the job interview.

The objective of this teaching unit is to present the problem of combinatorial optimization and the reference approaches to deal with such problems. It will make it possible to master the standard algorithms for solving operational research problems (dynamic programming, mathematical programming, branching algorithms, etc.). The teaching unit provides students with a basic culture in operational research, which makes them able to model a combinatorial optimization problem and to choose the appropriate approach to solve it and to evaluate it.

The objective of this teaching unit is an introduction to multilayer neural networks and their error gradient backpropagation learning algorithm. The SGD algorithm is presented and the problem of the disappearance of the gradient in deep architectures is highlighted. The various techniques for controlling this phenomenon are presented. Convolutional networks are then discussed, and highlighted for face recognition applications. Recurrent network architectures are presented for speech recognition. The architectures of adversary networks make it possible to approach the techniques of generation of false data. The objective is to understand and master modern supervised and weakly supervised learning techniques based on neural network architectures, and deep neural networks. Understand and master the optimization algorithms specific to these architectures. Know how to implement these algorithms using dedicated computing environments in Python language, such as Tensor Flow, Keras, or PyTorch.

The objective of this teaching unit is to allow the acquisition of a methodological approach, the implementation of a global approach taking into account the ecosystem of the field of embedded and real-time systems for the purpose of general understanding of the system. This requires awareness of the fundamental concepts of real-time embedded systems. This teaching unit will allow the design and production of complete prototypes of real-time communicating embedded systems based on Arduino or Raspberry Pi type cards.

This UE is a continuation of UE4 of S1 and completes training in HTML / CSS technologies with training in JavaScript which allows to implement dynamic behaviors (for example, interactions with the user) in Web documents. These three technologies are inseparable in client-side web design. At the end of this course, students will be able to enrich Web graphical interfaces (HTML/CSS documents) with user interaction behaviors, but also with richer and more sophisticated reactive web design mechanisms.

The objective of this teaching unit is to apply for at least 8 weeks the theoretical lessons received during the course period, within the framework of academic or industrial projects. The projects are carried out within the URN. The internship can be carried out in the laboratory or in a company.

The objective of this course is to present the basics of machine learning (the different types of contexts/tasks/applications), to understand how the main machine learning methods work, and to give the experimental methodological principles for setting up implementing these methods. The goal is to master the different tasks of machine learning, to understand the differences between the methods and their operating principle and to know how to set up an experimental protocol to test and compare these methods on real data sets. The topics covered are:

• Parametric and non-parametric, generative or discriminant classifiers (Gaussian estimation, Parzen estimator, k nearest neighbors, linear separator (perceptron, SVM))
• Hierarchical classifiers (decision trees)
• Neural networks (MLP)
• The selection of models

The objective of this teaching unit is to introduce the issue of the Web of data both from a historical and technical point of view. These are the technologies of the Semantic Web that make it possible to implement the fundamental principles of this Web of data. This is accompanied by a stack of standards issued by the World Wide Web Consortium (W3C) that this course offers to understand both theoretically and practically. The primary objective of this course is to enable students to acquire knowledge of the operation of the Semantic Web and its architectural principles. This is essential for a good understanding of today's Web given the growing role played by Semantic Web technologies. The secondary objective is to train in the standards of the Semantic Web in order in particular to achieve a concrete and mastered understanding of the notion of ontology and their ability to implement reasoning and deductions from new data. The targeted skills are:

• Understand the concept of Web of data and know the architectural principles of the Semantic Web.
• Master the representation languages adapted to the publication of linked data on the Web (RDF model).
• Master the main aspects of the SPARQL query language which allows the querying and modification of (linked) data through the Web.
• Understand the notion of ontology and the languages used to write them (RDFS, OWL, SKOS).

The objective of this teaching unit is to learn about graphic interface design with Web technologies. It aims to train in the use of HTML / CSS technologies for the creation of Web interfaces, with an emphasis on modern techniques of responsive web design. At the end of this course, students should be able to design multi-media adaptive graphical interfaces, that is to say that are functional on all types of screens (mobile, tablet, computers, etc.). This course does not cover concepts of ergonomics or graphics, but focuses on the technical mastery of dedicated tools. The targeted skills are:

• Master HTML5 for structuring web documents.
• Master the key principles of CSS for the formatting and visual and functional rendering of these pages.
• Master the fundamental techniques of responsive web design (flexible layout, flexible media, media queries, etc...).

The objective of this teaching unit is to present the theoretical and practical tools allowing the processing of random signals, in particular on aspects related to signal filtering. It is a question of mastering the classic approaches for such treatments. The targeted skills are:

• Theoretical deepening of signal processing tools.
• Putting into practice the methods seen in class.

The objective of this teaching unit is to know how to organize teamwork around a development project using AI:

• Know and implement the principles of team management (cycles, agility, etc.)
• Master common project management tools (diagrams, dashboards, version tracking, etc.)

The objective of this teaching unit is to present methods for finding the minimum of a function of R^n by descent with or without constraints, methods which are present in many learning algorithms. It is a question of mastering the theoretical aspects and of being able to implement these methods of descents

The objective of this teaching unit is to master classical and advanced unsupervised data analysis techniques for the purpose of data visualization or dimension reduction. It includes practical work sessions during which the methods are programmed in Python language. It is about understanding the assumptions behind the different data analysis models and implementing modern data analysis techniques

The objective of this teaching unit is to design professional documents (CV and cover letter) consistent with a professional objective and to prepare for the job interview.

This teaching unit must be selected, in agreement with the MinMacs tutor, from the catalog of teaching units of Masters participating in the MinMacs Graduate School

This teaching unit must be selected, in agreement with the MinMacs tutor, from the catalog of teaching units of Masters participating in the MinMacs Graduate School

The objective of this teaching unit is to present the problem of combinatorial optimization and the reference approaches to deal with such problems. It will make it possible to master the standard algorithms for solving operational research problems (dynamic programming, mathematical programming, branching algorithms, etc.). The teaching unit provides students with a basic culture in operational research, which makes them able to model a combinatorial optimization problem and to choose the appropriate approach to solve it and to evaluate it.

The objective of this teaching unit is an introduction to multilayer neural networks and their error gradient backpropagation learning algorithm. The SGD algorithm is presented and the problem of the disappearance of the gradient in deep architectures is highlighted. The various techniques for controlling this phenomenon are presented. Convolutional networks are then discussed, and highlighted for face recognition applications. Recurrent network architectures are presented for speech recognition. The architectures of adversary networks make it possible to approach the techniques of generation of false data. The objective is to understand and master modern supervised and weakly supervised learning techniques based on neural network architectures, and deep neural networks. Understand and master the optimization algorithms specific to these architectures. Know how to implement these algorithms using dedicated computing environments in Python language, such as Tensor Flow, Keras, or PyTorch.

The objective of this teaching unit is to deepen the fundamental theoretical concepts of machine learning in general, but also of the most emblematic generalist methods. At the end of this course, students will be familiar with the theoretical foundations of machine learning, will understand the motivations behind the different existing approaches and will master the operation of the most emblematic generalist methods.

The objective of this teaching unit is to deal with the different hardware architectures in the field of massive data processing as well as the methods and tools to make the best use of these different architectures. This teaching will address the hardware aspects, in particular memory (local or distributed on several machines) and different programming paradigms and tools on distributed architecture. The objective is to provide students with the basic knowledge and skills in distributed computing which make them able to use this type of infrastructure and to port their algorithms to such infrastructures and to familiarize them with the associated technologies (frameworks, files, etc.).

The objective of this teaching unit is to apply for at least 8 weeks the theoretical lessons received during the course period, within the framework of academic or industrial projects. The projects are carried out within the URN. The internship can be carried out in the laboratory or in a company.

This teaching unit must be selected, in agreement with the MinMacs tutor, from the catalog of teaching units of Masters participating in the MinMacs Graduate School

The objective of this teaching unit is to carry out a mini-laboratory research project.

This course presents the different architectures in the field of High Performance Computing (HPC): shared memory computers, distributed memory computers, GPU based accelerators... as well as the methods and tools to use these different architectures. This teaching will address the notions of computing power, profiling and optimization of computing performance, massively parallel computing and porting to GPUs. A focus will be made on the energy consumption of this type of infrastructure. The objective is to provide students with a basic culture of HPC, which will enable them to use this type of infrastructure and to improve their algorithms to adapt them to the use of such infrastructures. A second objective is to make students aware of the energy and environmental impact of using these infrastructures.

Skills and learning objectives:

• Use of HPC resources
• Identification and resolution of performance issues
• Parallelization of computational algorithms
• Adapting algorithms for use on GPUs

This course is one of the possible choices for UE 3: Machine Learning and Artificial Intelligence 1.

Program: (1) Demixing of audio sources, (2) Learning, regularization and optimization, (3) L2 vs L1 regularization, (4) L1 penalty example, (5) Subgradient and Fenchel duality, (6) Lagrangian duality, (7) sparse regression, (8) Ridge regression, (9) Lasso

Skills and learning objectives:

• Discover a panorama of recent statistical learning methods
• Master dictionary learning for signal and image representation (denoising)
• Know matrix factorization (example of recommendation systems)

This course is one of the possible choices for UE 3: Machine Learning and Artificial Intelligence 1.

The course chronologically describes the main algorithms and methods for sequence recognition, used in speech recognition, handwriting recognition, natural language processing, gesture analysis, and video analysis. The emphasis is on the algorithms rather than the applications: Hidden Markov Models, Conditional Random Fields, Neuro-Markovian Models, Recurrent Neural Networks, and Attention Models. These algorithms are partially implemented by the student during practical sessions, and then experimentally implemented on a problem of learning and recognition of sequences of handwritten symbols. The module evaluation consists of an oral presentation of the experimental results obtained by the student on the various topics covered in the practical sessions. The emphasis is on personal experiments that cannot be conducted during the practical sessions due to practical computational time constraints.

Goals:

• Understand and master the algorithms from the literature in sequence analysis.
• Master the experimental implementation of these algorithms on the topics proposed during the practical sessions, which lead to personal experimental work.

Skills and learning objectives:

• In-depth knowledge of statistical inference algorithms in sequences, "designer" approach.
• Experimental mastery of these algorithms implemented on one of the deep learning platforms such as TensorFlow or Pytorch.

This course is one of the possible choices for UE 3: Machine Learning and Artificial Intelligence 1.

This course presents an overview of learning methods applied to graph-based representations. After an introduction to graph-based representations and standard algorithms for manipulating such structures, approaches for matching graphs, computing dissimilarities between graphs or folding graphs into a Euclidean space are discussed. The course ends with a presentation of the most recent approaches to deep learning in graphs.

The objective is to provide students with a culture of graph data processing, with state-of-the-art methods.

Skills and learning objectives:

• Develop learning models on graphs
• Adapt models to the specificities of the processed data
• Analyze the performance of a learning model

This course is one of the possible choices for UE 3: Machine Learning and Artificial Intelligence 1.

In these courses we will see advanced methods in :

• Image denoising (bilateral filtering, NLM filtering, ROF model, deep image prior)
• Image segmentation with variational approaches (deformable active contours, level sets) as well as graph cut, NCut, Felzenschwab, superpixel methods (SLIC)
• Image segmentation with deep learning, using CNN (UNet) and Transformer (vision transformer)
• object detection (computer vision approaches, region proposal, deep learning architectures)
• DL architectures for denoising, style transfer, colorization, reconstruction, super-resolution, generative models (diffusion models)

Explainability in vision models will also be discussed.

Skills and learning objectives:

• know the current advanced image processing methods to perform low-level and high-level tasks in images

This course is one of the possible choices for UE 3: Machine Learning and Artificial Intelligence 1.

This course is an introduction to reinforcement learning. It aims at introducing the fundamental concepts and their modern transposition with deep learning tools. The program includes: (1) Bandit, (2) MDP, exact resolution, (3) Monte-Carlo methods, (4) Time difference, (5) Tabular methods, recursions, (6) Approximation by deep networks.

Skills and learning objectives:

• Implementation of a reinforcement learning environment
• Learning algorithms

This course is one of the possible choices for UE 3: Machine Learning and Artificial Intelligence 1.

Signal processing problems will be seen from the perspective of statistical learning. Program: (1) Random signals, (2) Stochastic linear systems, (3) Bayesian filter and estimation, (4) Kalman filter, (5) Particle filter, (6) Hidden Markov chain, (7) Break detection.

Skills and learning objectives:

• Use the machine learning paradigm to address signal processing issues.
• Acquire solid notions of statistical signal processing.
• Master the problems of estimation and detection of signals disturbed by random noise.

The objective of this course is to teach students how to read, summarize, comment on, and reproduce scientific articles, and to be able to establish a state of the art in a specific field.

Skills and learning objectives:

• Being able to perform targeted literature search using appropriate tools
• Having an understanding of scientific publications (conferences, journals)
• Being able to read, summarize, comment, and reproduce scientific articles, and being able to establish a state-of-the-art in a specific field

The aim of this course is to inform students about the functioning of a company and to help them adopt a professional attitude.

• The company, its different aspects
• The employee, rights and contracts
• Management, teamwork, brainstorming
• Project monitoring

This course is one of the possible choices of UE 1: Machine Learning and Artificial Intelligence 2.

This course will present the general principles of NLP, the different tasks in the field, the main models of Machine and Deep Learning

Goal:

• Know how to carry out a project of automatic processing of textual data by Machine and Deep Learning

Skills and learning objectives:

• Knowing how to prepare textual data
• Knowing how to train and evaluate NLP models
• Knowing how to choose a model adapted to the task

This course is one of the possible choices of UE 1: Machine Learning and Artificial Intelligence 2.

This course aims to master the use of mathematical and computer tools to create Computer Vision (CV) applications. The objective of this course is to cover all the tools used for CV applications, starting from geometric concepts (projective geometry, transformations) to object recognition, passing through image processing techniques used to detect and match primitives exploited in most CV applications.

Skills and learning objectives:

• Understand the mathematical tools involved in CV
• Apply the theoretical knowledge learned in class to develop CV applications
• Develop CV applications using the most widely used CV library: OpenCV

This course is one of the possible choices of UE 1: Machine Learning and Artificial Intelligence 2.

<

This course presents the problem of information retrieval. It presents different indexing and querying models, as well as preprocessing methods used to feed these models, and methodologies for evaluating and optimizing systems.

The objective is to provide students with an understanding of the problem of information retrieval and present the main models (binary, vectorial, probabilistic), specific treatments for text manipulation (segmentation, stemming, lemmatization...), as well as aspects of interaction with users aimed at optimizing results (relevance feedback, query disambiguation/expansion...).

Skills and learning objectives:

• Modeling an information retrieval problem
• Picking an information retrieval model for a specific problem
• Implementing text processing in order to feed these models
• Evaluation of information retrieval systems

This course is one of the possible choices of UE 1: Machine Learning and Artificial Intelligence 2.

This course focuses on the application problem of image search, a particular case of information retrieval, and more specifically on content-based image retrieval techniques. Within this framework, we address issues related to query modes, image representation (feature extraction, vector representation, local vs. global characterization of images, deep representation) for indexing and information retrieval, similarity calculation between representations, user feedback, performance, and scalability. We also cover object detection, spotting (word and pattern), and learning a model for image retrieval from few examples.

The objective is to present the evolution of the application domain of image search, particularly content-based image retrieval, and provide an overview of state-of-the-art image retrieval techniques.

Skills and learning objectives:

• Be able to design a content-based image retrieval system by evaluating the influence of the representation mode, the choice of similarity measure, and post-processing to ensure system reliability.
• Be able to develop a simple content-based image retrieval engine in Python, and evaluate its performance.
• Be able to develop a scalable engine in Python.
• Be able to compare different image retrieval systems.

This course is one of the possible choices of UE 1: Machine Learning and Artificial Intelligence 2.

Acquire the essential skills for the development of applications allowing human-machine interactions.

Goals:

• Acquire essential skills for developing applications that enable intuitive human-machine interactions adapted to the user and the context.
• Illustrate the concept of proactivity in an HMI that proposes behavior and/or adapted information, even when the user does not explicitly request it.
• Illustrate these concepts with concrete examples.
• Introduction to research (literature review, modeling and solving a scientific problem, etc.)

Skills and learning objectives:

• Formal models for interaction (automata, HMM, MAS, seq2seq, graphs, ...)
• Virtual and Augmented Reality (human-agent/robot interaction, mixed communities, ubiquitous computing, ...)
• Behavioral capture (gesture and facial expression recognition, categorization of behaviors, ...)
• Interactions (chatbots, embodied conversational agents, opinion mining, sentiment analysis, social network analysis)

This course is one of the possible choices of UE 1: Machine Learning and Artificial Intelligence 2.

The course is intended to give the students a fairly comprehensive view of fundamentals and techniques for combining multiple classifiers or machine learning models.

Goal:

• To master the art of combining classifiers.

Skills and learning objectives:

• Multiple Classifiers Systems (motivation, terminology, applications, taxonomy of fusion methods: sequential, parallel, hybrid architectures)
• Combining/fusion operators (class-based, rank-based, measure based; parametric, non parametric; stacking)
• Ensemble of classifiers (diversity in ensembles, cross-validated committees, bagging, boosting, random subspaces, ECOC, random forests and variants, XGBoost)

Individual project with a theoretical study, development and experiments. This project may constitute an initiation to research.

Application of the theoretical teachings received during the course period in the framework of academic or industrial projects

.

The internship can be carried out in a laboratory or in a company.

The subject of this course is server-side web design using Jakarta EE (formerly Java EE) technologies. Based on the various APIs of this platform, the course aims to describe the various server programming techniques in a conceptual and technical way, illustrated by concrete examples.

At the end of this course, students will be familiar with the various approaches to server-side web programming and will be technically capable of implementing them with Jakarta EE APIs or frameworks.

Skills and learning objectives:

• Knowing most of the APIs available on the Jakarta EE platform
• Mastering the implementation of the most basic APIs (Servlet, JSP, JSF, JAX, etc.)
• Understanding how today's most widely used Java frameworks (e.g. Spring) work.

This course is one of the possible choices for UE 3 : Machine Learning and Artificial Intelligence 1.

This course is not available for the SIME track (cf. the SD track).

This course is one of the possible choices for UE 3: Machine Learning and Artificial Intelligence 1.

The course chronologically describes the main algorithms and methods for sequence recognition, used in speech recognition, handwriting recognition, natural language processing, gesture analysis, and video analysis. The emphasis is on the algorithms rather than the applications: Hidden Markov Models, Conditional Random Fields, Neuro-Markovian Models, Recurrent Neural Networks, and Attention Models. These algorithms are partially implemented by the student during practical sessions, and then experimentally implemented on a problem of learning and recognition of sequences of handwritten symbols. The module evaluation consists of an oral presentation of the experimental results obtained by the student on the various topics covered in the practical sessions. The emphasis is on personal experiments that cannot be conducted during the practical sessions due to practical computational time constraints.

Goals:

• Understand and master the algorithms from the literature in sequence analysis.
• Master the experimental implementation of these algorithms on the topics proposed during the practical sessions, which lead to personal experimental work.

Skills and learning objectives:

• In-depth knowledge of statistical inference algorithms in sequences, "designer" approach.
• Experimental mastery of these algorithms implemented on one of the deep learning platforms such as TensorFlow or Pytorch.

This course is one of the possible choices for UE 3: Machine Learning and Artificial Intelligence 1.

This course presents an overview of learning methods applied to graph-based representations. After an introduction to graph-based representations and standard algorithms for manipulating such structures, approaches for matching graphs, computing dissimilarities between graphs or folding graphs into a Euclidean space are discussed. The course ends with a presentation of the most recent approaches to deep learning in graphs.

The objective is to provide students with a culture of graph data processing, with state-of-the-art methods.

Skills and learning objectives:

• Develop learning models on graphs
• Adapt models to the specificities of the processed data
• Analyze the performance of a learning model

This course is one of the possible choices for UE 3: Machine Learning and Artificial Intelligence 1.

In these courses we will see advanced methods in :

• Image denoising (bilateral filtering, NLM filtering, ROF model, deep image prior)
• Image segmentation with variational approaches (deformable active contours, level sets) as well as graph cut, NCut, Felzenschwab, superpixel methods (SLIC)
• Image segmentation with deep learning, using CNN (UNet) and Transformer (vision transformer)
• object detection (computer vision approaches, region proposal, deep learning architectures)
• DL architectures for denoising, style transfer, colorization, reconstruction, super-resolution, generative models (diffusion models)

Explainability in vision models will also be discussed.

Skills and learning objectives:

• know the current advanced image processing methods to perform low-level and high-level tasks in images

This course is one of the possible choices for UE 3: Machine Learning and Artificial Intelligence 1.

This course is an introduction to reinforcement learning. It aims at introducing the fundamental concepts and their modern transposition with deep learning tools. The program includes: (1) Bandit, (2) MDP, exact resolution, (3) Monte-Carlo methods, (4) Time difference, (5) Tabular methods, recursions, (6) Approximation by deep networks.

Skills and learning objectives:

• Implementation of a reinforcement learning environment
• Learning algorithms

This course is one of the possible choices for UE 3 : Machine Learning and Artificial Intelligence 1.

This course is not available for the SIME track (cf. the SD track).

Comparison of several development frameworks: native iOS, web-oriented hybrid (Ionic), non-web-oriented hybrid (Flutter).

The course aims to explore the different frameworks on the main aspects of mobile development: architecture, declarative user interface, navigation, asynchronous management.

In this course, we'll look at the network technologies and protocols that enable connectivity to be established at varying distances (on a local network or remotely via the Internet) between mobile terminals (smartphones, tablets) and between digital embedded systems (communicating objects), for more or less extensive data exchange, while complying with various constraints (energy consumption, volume of data exchanged, frequency of exchanges). In particular, we'll be looking at wireless network access technologies such as NFC, Bluetooth and WiFi, which are particularly well-suited to interaction between mobile terminals, as well as low-power, long-range wireless network technologies such as SigFox and LoRaWAN, which are widely used in sensor networks and the Internet of Things. We'll look at how these technologies work, and compare them in terms of their advantages and disadvantages. We'll also look at the routing of information packets in connected object networks, and study the 6loWPAN protocol, an adaptation of the IPv6 protocol for routing IP datagrams on these networks, as well as transport and application protocols adapted to the IoT, such as MQTT and coAP.

The aim is to be able to design and develop applications involving interaction between mobile terminals, or to equip on-board digital systems with means of communication in order to obtain communicating digital objects, capable of exchanging information, and with which it is possible to interact remotely via the Internet.

Compétences et apprentissages visés :

• Compréhension du fonctionnement des technologies abordées
• Être capable de faire des choix de technologies et de mise en œuvre en fonction des contraintes spécifiées par le cahier des charges
• Maîtrise des protocoles étudiés
• Être capable d'analyser une architecture réseau et d'en effectuer la simulation sur un simulateur réseau tel que Cisco Packet Tracer
• Être capable d'effectuer la configuration réseau des éléments d'un réseau de terminaux mobiles et objets connectés
• Être capable d'analyser les trames d'information et de supervision échangées par les différents protocoles de communication étudiés à l'aide d'un outil d'analyse de trames

The aim is to master the development of powerful, reliable and scalable embedded robotic applications.

Compétences et apprentissages visés :

• Installer et configurer l'environnement et les outils nécessaires pour la programmation ROS2
• Savoir utiliser l’ensemble des concepts sous-jacents à ROS2 (Topics, Noeuds, Services, Fichiers, Interfaces)
• Implémentation sur bras robotique Niryo Ned

Study and comparison of different architectures dedicated to the development and implementation of machine learning solutions. In particular, this course will focus on embedded machine learning.

The aim is to learn about and use the main architectures dedicated to machine learning (GPU, TPU, etc.).

Teamwork: Design and production of a mobile and/or embedded solution to meet the needs of an external partner.

Skills and learning objectives:

• Draw up specifications and identify the functional requirements of a customer issue
• Implement project management tools within a team of approx 6 students

The aim of this course is to inform students about the functioning of a company and to help them adopt a professional attitude.

• The company, its different aspects
• The employee, rights and contracts
• Management, teamwork, brainstorming
• Project monitoring

This course is one of the possible choices of UE 1: Machine Learning and Artificial Intelligence 2.

This course will present the general principles of NLP, the different tasks in the field, the main models of Machine and Deep Learning

Goal:

• Know how to carry out a project of automatic processing of textual data by Machine and Deep Learning

Skills and learning objectives:

• Knowing how to prepare textual data
• Knowing how to train and evaluate NLP models
• Knowing how to choose a model adapted to the task

This course is one of the possible choices of UE 1: Machine Learning and Artificial Intelligence 2.

This course aims to master the use of mathematical and computer tools to create Computer Vision (CV) applications. The objective of this course is to cover all the tools used for CV applications, starting from geometric concepts (projective geometry, transformations) to object recognition, passing through image processing techniques used to detect and match primitives exploited in most CV applications.

Skills and learning objectives:

• Understand the mathematical tools involved in CV
• Apply the theoretical knowledge learned in class to develop CV applications
• Develop CV applications using the most widely used CV library: OpenCV

This course is one of the possible choices of UE 1: Machine Learning and Artificial Intelligence 2.

<

This course presents the problem of information retrieval. It presents different indexing and querying models, as well as preprocessing methods used to feed these models, and methodologies for evaluating and optimizing systems.

The objective is to provide students with an understanding of the problem of information retrieval and present the main models (binary, vectorial, probabilistic), specific treatments for text manipulation (segmentation, stemming, lemmatization...), as well as aspects of interaction with users aimed at optimizing results (relevance feedback, query disambiguation/expansion...).

Skills and learning objectives:

• Modeling an information retrieval problem
• Picking an information retrieval model for a specific problem
• Implementing text processing in order to feed these models
• Evaluation of information retrieval systems

This course is one of the possible choices of UE 1: Machine Learning and Artificial Intelligence 2.

This course focuses on the application problem of image search, a particular case of information retrieval, and more specifically on content-based image retrieval techniques. Within this framework, we address issues related to query modes, image representation (feature extraction, vector representation, local vs. global characterization of images, deep representation) for indexing and information retrieval, similarity calculation between representations, user feedback, performance, and scalability. We also cover object detection, spotting (word and pattern), and learning a model for image retrieval from few examples.

The objective is to present the evolution of the application domain of image search, particularly content-based image retrieval, and provide an overview of state-of-the-art image retrieval techniques.

Skills and learning objectives:

• Be able to design a content-based image retrieval system by evaluating the influence of the representation mode, the choice of similarity measure, and post-processing to ensure system reliability.
• Be able to develop a simple content-based image retrieval engine in Python, and evaluate its performance.
• Be able to develop a scalable engine in Python.
• Be able to compare different image retrieval systems.

This course is one of the possible choices of UE 1: Machine Learning and Artificial Intelligence 2.

Acquire the essential skills for the development of applications allowing human-machine interactions.

Goals:

• Acquire essential skills for developing applications that enable intuitive human-machine interactions adapted to the user and the context.
• Illustrate the concept of proactivity in an HMI that proposes behavior and/or adapted information, even when the user does not explicitly request it.
• Illustrate these concepts with concrete examples.
• Introduction to research (literature review, modeling and solving a scientific problem, etc.)

Skills and learning objectives:

• Formal models for interaction (automata, HMM, MAS, seq2seq, graphs, ...)
• Virtual and Augmented Reality (human-agent/robot interaction, mixed communities, ubiquitous computing, ...)
• Behavioral capture (gesture and facial expression recognition, categorization of behaviors, ...)
• Interactions (chatbots, embodied conversational agents, opinion mining, sentiment analysis, social network analysis)

This course is one of the possible choices of UE 1: Machine Learning and Artificial Intelligence 2.

The course is intended to give the students a fairly comprehensive view of fundamentals and techniques for combining multiple classifiers or machine learning models.

Goal:

• To master the art of combining classifiers.

Skills and learning objectives:

• Multiple Classifiers Systems (motivation, terminology, applications, taxonomy of fusion methods: sequential, parallel, hybrid architectures)
• Combining/fusion operators (class-based, rank-based, measure based; parametric, non parametric; stacking)
• Ensemble of classifiers (diversity in ensembles, cross-validated committees, bagging, boosting, random subspaces, ECOC, random forests and variants, XGBoost)

Processing and formatting of data received from a webservice and the mobile terminal, data persistence on the mobile terminal, management of background requests and responses.

The aim is to know how to carry out webservice-type requests within an Android application architecture, asynchronously and possibly in the background; store data in a local database; manage access permissions to data provided by a mobile terminal.

Study of mobile and embedded solutions in a complex environment requiring the use of machine learning.

The aim is to design solutions that coordinate:

• A pre-existing machine learning model or one trained on a dedicated architecture
• A mobile or embedded system to operate the model locally or remotely

Teamwork: Design and production of a mobile and/or embedded solution to meet the needs of an external partner.

Skills and learning objectives:

• Draw up specifications and identify the functional requirements of a customer issue
• Implement project management tools within a team of approx 6 students

Application of the theoretical teachings received during the course period in the framework of academic or industrial projects

.

The internship can be carried out in a laboratory or in a company.