Data Science Master's program / Data Science Track

Course label :	Python and tools for research
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S1_PTR - Python and tools for research

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Basic notions and structures of Python and popular modules (numpy, scipy, sklearn, etc.). Fundamentals of object-oriented programming with Python. Hands on, plus some presentation of useful tools such as LaTex and Bibtex. The labs will illustrate: - the ability of Python to quickly translate into code very usual linear algebra operations as well as statistical procedures; - the benefits of object-oriented programming (with ML oriented examples); - the power of Latex/Bibtex for scientific document editing.

Educational goals

After successfully taking this course, students should be able to: - manipulate usual structures of Python; - implement object-oriented programs in Python; - understand the notion of class and object; - understand the concepts of encapsulation and inheritance; - write Python code abiding by usual notation, comment and documentation conventions; - systematically test their codes (through unit tests, debugging); - use several ML-oriented Python modules (numpy, scipy, sklearn); - write a report using LaTex and Bibtex; - explore bibliographic databases and administrate a bibliography.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Continuous evaluation. Labs, grading scale: (min) 0 = 20 (max) - Passing grade = 10/20 Evaluations: - LaTeX report (L): 6h - Python lab reports (P) x4: 2h each Grade session 1: N = (L+4*P) / 5 2nd chance evaluation : Python lab (2h) (TP) Grade session 2: 0.7*N + 0.3*TP

Online resources

List of references, documents, .tex resources and lab notebooks, made available on Moodle.

Pedagogy

Lab sessions. Language of instruction: English.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Basics of programming in Python. Refresher course in computer science. Basic notions of C programming.

Maximum number of registrants

Remarks

Assessment based on the reports and codes produced for each lab by each group of students (composed of max. 2 students).

Course label :	Refresher in Computer Science
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S1_RCS - Refresher in Computer Science

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Fundamentals of object oriented programming, with a strong focus on the Python programming language. This course emphasizes the theoretical fundamentals of object oriented programming with hands-on training for rapidly prototyping applications. The practicals will illustrate : ● the benefits of object oriented programming, ● the ability of Python to quickly translate ideas into code, ● the process of developing and scaling a proof-of-concept, and preparing for production. Some of the frameworks and tools we will utilize are : ● pyTest, cProfile, pycallgraph, Pylint, Travis, asyncio, zeroMQ, Docker, Flask.

Educational goals

After successfully taking this course, a student should: ● understand the notions of class and object, ● understand the concepts of encapsulation and inheritance, ● understand the most common design patterns used in object oriented programming, ● understand the principle of inversion-of-control through dependency injection, ● lay the groundwork for testing, analyzing and profiling software, ● learn to leverage continuous integration in the development process, ● learn to package and prepare an application for production, ● learn to scale applications through asynchronous parallelization, ● learn to quickly prototype applications with simple web frontends.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Labs, grading scale: (min) 0 – 20 (max) Exam, grading scale: (min) 0 – 20 (max)

Online resources

Design Patterns: Elements of Reusable Object-Oriented Software. Erich Gamma, Richard Helm, Ralph Johnson, John Vlissides. Python Programming: An Introduction to Computer Science. John Zelle. Clean Code: A Handbook of Agile Software Craftsmanship. Robert C. Martin Series. Flask Web Development: Developing Web Applications with Python. Miguel Grinberg. Continuous Delivery: Reliable Software Releases through Build, Test, and Deployment Automation. Jez Humble, David Farley.

Pedagogy

24 hours, 8 lectures 4 exercises Language of instruction is specified in the course offering information in the course and programme directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Basics of programming in Python.

Maximum number of registrants

Remarks

Course label :	Refresher in Maths
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S1_RMA - Refresher in Maths

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

• Linear algebra (14h) ◦ Matrices and linear systems of equations. Null space, column space and rank theorem. ◦ Trace, determinant, eigenvectors and eigenvalues. • Multivariable calculus (10h) ◦ Multivariable vector and scalar functions. Continuity, partial derivatives and differentiability. ◦ Matrix representation of the differential. Properties of differentiable functions.

Educational goals

After successfully taking this course, a student should be able to: • Use/understand standard notions for forthcoming courses of the Master program • Have basic notions of linear algebra and multivariate differential calculus

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Assessment is based on a homework assignment (HW) and a final examination (EX) during the final session, each giving a mark out of 20. The final mark will be calculated as follows: 0.5*HW+0.5*EX. Grading scale: (min)0 – 20 (max) - Pass = 10/20 Second chance: For those who would not achieve a pass grade, there will be a second chance associated with a second homework (HW2). The second chance grade is calculated as follows: 0.2*EX+0.4*HW+0.4*HW2.

Online resources

1. S. Lang, Undergraduate Analysis, Springer, 1997 2. G. Strang, Introduction to linear algebra, Wellesley-Cambridge 2016. 3. G. Strang, Linear algebra and learning from data, Wellesley Cambridge Press, 2019

Pedagogy

Language of instruction is specified in the course offering information in the course and programme directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Basics of linear algebra (matrices, vectors…)

Maximum number of registrants

Remarks

Course label :	Algorithms and their complexity 1
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S1_AC1 - Algo and their complexity 1

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

The course will cover the following topics: • Fundamental properties of algorithms. • Algorithm writing with pseudo-code. • Recursion. • Formal notational methods for stating the growth of resource needs (efficiency and storage) of an algorithm (Big Oh, Little oh, Theta notations). • Time and space complexity. • Best-case and worst-case complexity. • Divide-and-conquer paradigm. • Backtracking. • Branch-and-bound. • Dynamic programming. • Greedy algorithms.

Educational goals

This course gives an overview about algorithms and computation with a particular focus on the cost of algorithms. The overall goal is to be able to understand a range of algorithmic approaches, use them to solve practical problems, evaluate their cost, and compare the costs of different algorithms solving a given problem. After successfully taking this course, a student should be able to: • Write recursive algorithms, • Understand the following families of algorithms and use them to solve problems: divide-and-conquer, backtracking, branch-and-bound, dynamic programming, greedy algorithms. • Understand and evaluate the time and space complexity of an algorithm. • Analyze worst-case and best-case running times of algorithms using asymptotic analysis. • Derive and solve recurrences describing the performance of recursive and divide-and-conquer algorithms.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Quizzes, grading scale: (min) 0 – 20 (max) Homework, grading scale: (min) 0 – 20 (max)

Online resources

Introduction to Algorithms (Thomas H. Cormen, Charles E. Leiserson, Ronald L. Rivest Clifford Stein) – McGraw-Hill.

Pedagogy

24 hours : 8 lectures, 8 tutorials. Language of instruction is specified in the course offering information in the course and program directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

This course requires some basic programming knowledge (expressions, variable, control flow statements, functions, arrays or lists) and some fundamental notions of mathematics (functions and sequences, recurrence relations). The knowledge of specific programming languages is not required.

Maximum number of registrants

Remarks

Course label :	Databases
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S1_DBA - Databases

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

The course will cover the following topics: • Reminder about SQL, relational algebra and logic • Indexes and materialized views: advantages, drawbacks and when to use them • Using various kinds of indexes in the design of a database, • Physical plan of a query execution and the evaluation of its incurred cost, • Logical plan and optimization of a query and their cost models, • Query tuning.

Educational goals

At the end of the course, a successful student should be able to master the main techniques and algorithms that allow relational databases to handle efficiently large amount of data. These methods form the bases of systems that handle larger amounts of data. After attending this course the successful student will be able to: • Understand the relationship between relational algebra, logic, SQL, • Write complex queries, • Use methods to improve the performance of a database, • Know various structures of indexes and when to use them, • Understand how queries are compiled, optimized and executed, • Tune queries so as to make them more efficient.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Labs, grading scale: (min) 0 – 20 (max) Exam, grading scale: (min) 0 – 20 (max) Average passing grade = 10/20

Online resources

“Database systems, the complete book”, second edition, H. Garcia-Molina, J. D. Ullman, J. Widom “Database management systems”, third edition, R. Ramakrishnan, J. Gehrke “Database system concepts”, sixth edition, A. Silberschatz, H. Korth, and S. Sudarshan

Pedagogy

24 hours, 6 lectures 6 exercises Language of instruction is specified in the course offering information in the course and program directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Introductory knowledge in SQL, programming and in algorithms.

Maximum number of registrants

Remarks

Course label :	Fundamental notions of Mathematics
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S1_FNM - Fundamental notions of Math

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

• Linear algebra (8h) ◦ Hermitian spaces, scalar product, projection matrices, orthogonal (unitary) and symmetric (self-adjoint) matrices. ◦ least squares problems ◦ matrix norms ◦ Singular Value Decomposition (SVD) and applications • Differential calculus and optimization (8h) ◦ functions of several variables, gradient, hessian ◦ application to gradient descent and convex problem ◦ optimization problems without and with constraints • Integration (8h) ◦ curves in R^d : line integrals and surface integrals ◦ multiple integrals: Fubini’s theorem ◦ change of variables ◦ surfaces in R^d and surface integrals ◦ Stokes theorem

Educational goals

After successfully taking this course, a student should be able to: • Think geometrically about linear algebra on Hermitian spaces • Optimize a function of several variables • Compute integrals in several variables

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Exam, grading scale: (min) 0 – 20 (max) Average passing grade = 10/20

Online resources

S Lang , Undergraduate Analysis, Springer (1997) S.DIneen, Multivariate calculus and Geometry, Springer G. Strang, Linear Algebra and Learning from Data, Wellesley-Cambridge Press

Pedagogy

24 hours, 8 lectures 4 exercises Language of instruction is specified in the course offering information in the course and program directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Bases of linear algebra, integration and analysis.

Maximum number of registrants

Remarks

Course label :	Probability 1
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S1_PR1 - Probability 1

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Fundamentals of probability and integration. First applications. - Probability space: the triplet (set, sigma-algebra, measure), examples (2h) - Random variables, random vectors, random element, examples (2h) - Expectation, variance, covariance, independence (2h) - Gaussian vectors: definition, density, rotational invariance (4h) - Projection’s theorem, L^2 space, conditional expectation, examples (Gaussian, ...) (4h) - Modes of convergence: in distribution, in probability, almost surely, L^p, examples (LLN) (2h) - Classical probability distributions and models (4h) - Characteristic function, the central limit theorem, examples (4h)

Educational goals

After successfully taking this course, a student should: • understand the mathematical structures of probabilistic modeling • be able to compute the main features of probabilistic models: location and scale parameters

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Exam, credits, grading scale: (min) 0 – 20 (max) - Passing grade = 10/20

Online resources

1. https://www.statlect.com/fundamentals-of-probability/ 2. “Probability and Measure”, P. Billingsley 3. “Aléatoire”, S. Méléard

Pedagogy

24 hours, 8 lectures 4 exercises sessions Language of instruction is specified in the course offering information in the course and programme directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Fundamental notions of mathematics.

Maximum number of registrants

Remarks

Course label :	Statistics 1
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S1_ST1 - Statistics 1

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

• Data types and description of the distribution of univariate random variables: probability distribution / density function, cumulative distribution function, quantile functions, moments (mean, variance, skewness, kurtosis) Graphical representations: pie charts, barplots, histograms, boxplots, … • Confidence intervals. • Bivariate statistical analyses: Mean comparisons with t-tests or ANOVA (when one variable is qualitative, the other one quantitative), chi-squared independence tests (when the variables are both qualitative), correlation analysis (when the variables are both quantitative) • Classifiers: introduction to decision theory and ROC curves. The course will be illustrated by many examples on computer, using the R software.

Educational goals

After successfully taking this course, a student should be able to: • use standard statistical exploration tools from descriptive statistics and have a sound approach of data • be aware that assertions should be statistically tested, and be able to provide scientific evidence of what is read from the data

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Grading scale: (min) 0 – 20 (max) Passing grade = 10/20

Online resources

1. Mathematical statistics, Vol. 1&2, P.J. Bickel, K.A. Doksum, CRC Press, Chapman and Hall, 2015 2. Introduction to Probability and Statistics Using R by G. Jay Kerns http://ipsur.r-forge.r-project.org/book/ 3. Introduction to R by Andrew Ellis, Boris Mayer https://methodenlehre.github.io/SGSCLM-R-course/

Pedagogy

24 hours, including lectures and exercise sessions Language of instruction is specified in the course offering information in the course and programme directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

None

Maximum number of registrants

Remarks

Course label :	Machine learning 1
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister LOUIS FILSTROFF / Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S1_ML1 - Machine learning 1

Education team

Teachers : Mister LOUIS FILSTROFF / Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Introduction to machine learning (ML), emphasizing the link with the other classes within the programme of the master's degree (ML2, probability, optimization). Several hands-on practical sessions in Python are aimed at building knowledge on the main concepts, covering: - scikit-learn basics; - data cleaning; - basics in plotting; - designing, implementing, testing, and evaluating an ML pipeline.

Educational goals

After successfully taking this course, a student should be able to: - identify a category of problems, in light of the available data and the nature of the parameters to learn (classification, regression, dimensionality reduction); - understand the main objectives of machine learning (ML) and the main approaches; - know the basic principles behind classical ML algorithms; - understand the first limits and requirements to conduct a ML project; - understand the notion of error and the principle of (regularized) empirical risk minimization (ERM); - use Python to implement ML algorithms, test them, and evaluate their performances; - access and preprocess data using Python.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Labs, grading scale: (min) 0 – 20 (max) Exam, grading scale: (min) 0 – 20 (max) Average passing grade = 10/20 1. Continuous assessment activities and duration: - 1 intermediate written exam (20 min) (exam1, /10) - 1 final written exam (1h) (exam2, /20) - 2 graded lab reports (2h each) (lab1, lab2) 2. Computation of the overall grade: - `Mark1 = 0.125*(exam1 * 2) + 0.375*exam2 + 0.25*lab1 + 0.25*lab2` 3. If Mark1 < 10/20: - 2nde chance exam : 1 written exam (2h) (exam3) - final grade after 2nd chance exam (if required): `Mark2 = 0.6 * Mark1 + 0.4 * exam3`

Online resources

- Shalev-Shwartz and Ben-David (2014). Understanding Machine Learning: From Theory to Algorithms, Cambridge University Press, 2014 - Bishop, C. M., & Nasrabadi, N. M. (2006). Pattern recognition and machine learning (Vol. 4, No. 4, p. 738). New York: Springer.

Pedagogy

- Labs (6h) and tutorial sessions (2 x 2h). - Final exam (2h). - Language of instruction: English.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Basic knowledge of a programming language such as Python; notions on algorithms and fundamental notions of mathematics (linear algebra, notions in probability and optimization).

Maximum number of registrants

Remarks

Continuous evaluation, based on: - lab report(s), 50% of the overall grade, grading scale: (min) 0 – 20 (max) - 2 exams, 50% of the overall grade, grading scale: (min) 0 – 20 (max) 2nd chance exam (session 2): - grade on 20 points - final grade for the course: 60% session 1 (grade at the continuous assessment), 40% session 2

Course label :	Machine learning 2
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S1_ML2 - Machine learning 2

Education team

Teachers : Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Educational goals

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Maximum number of registrants

Remarks

Course label :	Ethics and Laws
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S1_ELA - Ethics and Laws

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

• Ethics and right of data, complementarity or competition? The place of codes of conduct and certification. • Personal data : notion and sources of notion and sources of regulation • Non personal data and public data : notions and sources of regulation • The person concerned by data processing, the person responsible for data processing • Main principles of RGPD (european regulation) • Legal causes of data processing: agreement and consent • Legal causes of data processing: the legitimate interest in collecting data • Rights and obligations of the person concerned by data • Rights and obligations of the person responsible for data processing • Transfer of personal data toward other countries or international organisations • The delegate to data protection • The french CNIL, the european committee for data protection, the european

Educational goals

The goal of this course is to give students insights in the main aspects of right and ethics as far as data analysis is concerned.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Exam, grading scale: (min) 0 – 20 (max) - Passing grade = 10/20

Online resources

Pedagogy

24 hours, 12 lectures. Language of instruction is specified in the course offering information in the course and program directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

None

Maximum number of registrants

Remarks

Course label :	English
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S1_ANG - Anglais

Education team

Teachers : Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Educational goals

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	0
Number of hours - Tutorial :	24
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Maximum number of registrants

Remarks

Course label :	FLE
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Madam HAKIMA LARABI / Madam VERONIQUE DZIWNIEL
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S1_FLE - FLE ou 2nde langue

Education team

Teachers : Madam HAKIMA LARABI / Madam VERONIQUE DZIWNIEL
External contributors (business, research, secondary education): various temporary teachers

Summary

Educational goals

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	0
Number of hours - Tutorial :	24
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Maximum number of registrants

Remarks

Course label :	LV2
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S1_LV2 - LV2 au choix

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Educational goals

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	0
Number of hours - Tutorial :	24
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Maximum number of registrants

Remarks

Course label :	Algorithms and their complexity 2
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S2_AC2 - Algo and their complexity 2

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

The course will cover the following topics: • Tractable and intractable problems. • NP-algorithms, NP-hardness, NP-completeness. • Reductions. • NP-hard problems and linear programing. • Hard problems: Traveling salesman problem, Longest path, Hamilton cycle, Boolean circuit satisfiability, Clique, Vertex cover, Correlation Clustering. • Basic notions of probability (conditional probability, the law of total probability). • Approximation algorithms. • Analysis of approximation algorithms for graph problems. • Random graphs and basic notions related to random walk. • Hashing algorithms. Searching using Hashing. Hash tables. Hash functions. Some examples of hash functions. Collision resolution. • Basic problems related to randomized algorithms (e.g., Coupon Collector’s problem , Balls and Bins, …). • Chernoff Bound and its basic applications in the analysis of randomized algorithms. • Basic properties of randomized algorithms and methods for analyzing them. • Advanced data structures to solve specific problems taking into account computational constraints.

Educational goals

The goal of this course is to provide advanced algorithmic and computation notions covering the main topics related to randomized algorithms, relationships between different complexity classes, reductions and approximation algorithms. After successfully taking this course, a student should be able to: • Analyze average-case running times of algorithms whose running time is probabilistic. Employ indicator random variables and linearity of expectation to perform the analyses. • Manipulate problem reductions. • Know the relationships between different specific complexity classes (including complexity classes P, NP, L, NL, PSPACE, BPP, #P). • Design heuristics for complex problems. • Apply important algorithmic design paradigms and methods of analysis. • Argue the correctness of algorithms using inductive proofs. • Explain the basic properties of randomized algorithms and methods for analyzing them. Design algorithms that employ randomization. • Explain advanced graph algorithms and their analysis. • Design and analyze approximation algorithms.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Labs, grading scale: (min) 0 – 20 (max) Exam, grading scale: (min) 0 – 20 (max)

Online resources

Introduction to Algorithms (Thomas H. Cormen, Charles E. Leiserson, Ronald L. Rivest e Clifford Stein) – McGraw-Hill.

Pedagogy

24 hours, 8 lectures 4 exercises. Language of instruction is specified in the course offering information in the course and program directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

This course requires some programming knowledge and a background in algorithms and data structures, with a good understanding of the fundamental notions of probability. Algorithms and their complexity 1.

Maximum number of registrants

Remarks

Course label :	Numerical analysis and optimization
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S2_NAO - Numerical analysis and optim

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

- Convexity, Lipschitz continuity - Unconstrained optimization problems - Back to Empirical Risk Minimization, Machine Learning and regularization - Convergence analysis. - Stochastic Descent method Like many engineering issues, machine learning problems express as a continuous optimization problem: given a Lipschitz continuous objective function, we are looking for the parameters that minimize it. Here, the set of admissible parameters will be a convex set, often a convex polyhedron. Most of the time, finding exact minimizers is not possible and we are looking for parameters that provide a good approximation of the theoretical minimal value of the objective function. In practice, we use algorithms that improve iteratively these parameters. The lectures present the basic theory of convex optimization and the associated efficient algorithms together with applications to Machine Learning. We start by recalling some facts about unconstrained convex optimization and about the associated gradient descent algorithms (first order and Newton-like higher order methods). We will show how this applies to Neural networks and present important variations such as the Stochastic Descent Method.

Educational goals

After successfully taking this course, a student should be able to: ● identify convex and non-convex problems ● compute convergence rates of some approximation methods for some optimization problems ● formulate a machine learning problem as an optimization problem ● know which methods may be used to solve such a problem; know how to use them in practice.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Average passing grade = 10/20 - Labs, grading scale: (min) 13.5 – 20 (max) Exam, grading scale: (min) 6.5 – 20 (max)

Online resources

Stephen Boyd and Lieven Vandenberghe. Convex Optimization. Cambridge University Press. Vanderbei, Linear Programming: Foundations and Extensions, Springer 2014

Pedagogy

24 hours, 8 lectures 4 exercises Language of instruction is specified in the course offering information in the course and programme directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Machine learning 1, Machine Learning 2, Python & tools for research, or their equivalent.

Maximum number of registrants

Remarks

Course label :	Probability 2
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S2_PR2 - Probability 2

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

The lecture introduces the most important notions associated to discrete-time Markov chains (transition matrix, recurrent and transient states, invariant measure, convergence in large times), and then presents a few applications: queuing theory (with generalization in continuous time), Metropolis-Hastings algorithm and Simulated Annealing algorithm. 1. Markov Chains in discrete time 2. Poisson Processes and Queues 3. Monte Carlo Methods (Metropolis-Hastings algorithm), simulated annealing

Educational goals

- Be able to analyze a discrete-time Markov chains, its characteristics and its large time behavior. Simulate Markov chains in Python. - Compute the invariant measure associated to a queue process, and analyze its behavior - Implement Metropolis-Hastings algorithm and Simulated Annealing algorithm

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: 1 homework, 2 graded lab reports, final exam Labs, grading scale: (min) 0 – 20 (max) - Passing grade = 10/20 Weights of the activities in the final grade: (DM*2 + exam*5 + TP1*1,5 + TP2*1,5)/10

Online resources

Pedagogy

Lectures (6x2h), tutorial sessions (6x2h, including 2x2h practical sessions) Language of instruction: English.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Notions in probability and Python programming.

Maximum number of registrants

Remarks

Course label :	Statistics 2
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S2_ST2 - Statistics 2

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

• Estimators: bias, variance. Consistency, bias-variance decomposition. • Likelihood and maximum likelihood estimators. Exponential families. • Fisher information, Cramer-Rao bound lower bound on the variance of an unbiased estimator. • Asymptotic normality, Delta-method. • Asymptotic properties of the maximum likelihood estimators and associated tests • Likelihood-ratio tests, Uniformly more powerful tests • Mixture models, EM algorithm. All methods will be illustrated in practical sessions using Python.

Educational goals

After successfully taking this course, a student should be able to: • master the techniques of mathematical statistics.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Final Exam, grading scale: (min) 0 – 20 (max) Labs, grading scale: (min) 0 – 20 (max) The final grade is the average of the exam and the labs grades. Passing grade is 10/20.

Online resources

1. Larry Wasserman, All of Statistics, A concise course in statistical inference.Springer, 2003. 2. A.Van der Vaart, Asymptotic Statistics. Cambridge University Press, 1998. 3. Vincent Rivoirard and Gilles Stoltz, Statistique en Action. Vuibert, 2009.

Pedagogy

24 hours, 6 lectures, 4 exercise sessions, 2 labs Language of instruction is specified in the course offering information in the course and programme directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Probability 1. Statistics 1.

Maximum number of registrants

Remarks

Course label :	Machine learning 3: Deep learning
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S2_ML3 - Machine learning 3: Deep learn

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

● reminder (ML1) + some complements: introduction to formal neural networks, the perceptron, training a perceptron, multilayer perceptron, full presentation of the backpropagation of the gradient of the error (incl. tricks to make it work in practice) ● elements of the formal analysis of neural networks (incl. MLP and their approximation ability) ● limitations of the classical MLP + backprop approach (vanishing or exploding gradient, etc.) ● the renewal of neural networks: deep learning and convolutional networks (conv / pool layers) ● deep net as a representation learner (auto-encoders, restricted Boltzmann machines) ● efficient deep net training (batch normalization, dropout, regularization etc.) ● recurrent neural networks and long-short time memories ● generative adversarial networks.

Educational goals

After successfully taking this course, a student should: ● know and understand the main concepts related to neural networks ● know the main types of neural networks (feedforward, convolutional, recurrent) and neurons ● know the main algorithms to train a neural network in practice ● understand the design of a deep neural network ● know how to use a neural network in practice to solve a particular supervised learning problem ● understand the limits of neural networks ● know theoretical properties of deep nets

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Labs, grading scale: (min) 0 – 20 (max) Exam, grading scale: (min) 0 – 20 (max)

Online resources

Hastie & Tibshirani, The Elements of Statistical Learning, Springer 2009. Goodfellow, Bengio, Courville, The Deep Learning book, MIT Press, 2016.

Pedagogy

24 hours, 6 lectures 6 exercises / labs Language of instruction is specified in the course offering information in the course and programme directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

ML1. ML2. Python & tools for research. Bases of optimization.

Maximum number of registrants

Remarks

Course label :	Models for Machine Learning
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S2_MML - Models for Machine Learning

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN
External contributors (business, research, secondary education): various temporary teachers

Summary

Fundamentals of Bayesian models and inference. Hands on sessions. Usual methods and notions in this scope are summarized below: - baseline concepts (likelihood, prior, posterior, predictive distribution) - conjugate priors, uninformative priors, exponential family; - Bayesian estimators (ML, MAP, MMSE, type 2 ML, type 2 MAP, ...); - hierarchical models; - graph representation with directed acyclic graphs (DAGs); - Monte Carlo, exact inference with Markov chain Monte Carlo algorithm (MCMC) (Metropolis-Hastings, Gibbs sampler, effective sample size (ESS)).

Educational goals

After successfully taking this course, a student should be able to: - identify a relevant model in light of the available data; - formalize the learning problem as an optimization problem; - identify the nature of the distributions involved in the learning problem (posterior distribution, predictive distribution, marginals,full conditionals, ...); - understand the connections between deterministic and probabilistic modelings; - understand the implications of the chosen model on the results; - implement a simple approach to solve a statistical problem (MCMC algorithm).

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Continuous evaluation, based on: - lab report(s), 50% of the overall grade, grading scale: (min) 0 – 20 (max) - final exam, 50% of the overall grade, grading scale: (min) 0 – 20 (max) 2nd chance exam (session 2): - grade on 20 points - final grade for the course: 50% session 1 (grade at the continuous assessment), 50% session 2 Labs, grading scale: (min) 0 – 20 (max) Exam, grading scale: (min) 0 – 20 (max)

Online resources

- Robert, C. P. (2007). The Bayesian choice: from decision-theoretic foundations to computational implementation (Vol. 2). New York: Springer. - Bishop, C. M., & Nasrabadi, N. M. (2006). Pattern recognition and machine learning (Vol. 4, No. 4, p. 738). New York: springer. - Murphy, K. P. (2012). Machine learning: a probabilistic perspective. MIT press. - Jones, Galin L and Qin, Qian (2022). Markov Chain Monte Carlo in Practice, Annual Review of Statistics and Its Application (Vol. 9, pp. 557-578) - Robert, C. P., Casella, G., & Casella, G. (1999). Monte Carlo statistical methods (Vol. 2). New York: Springer.

Pedagogy

Labs (4h) and tutorial sessions (3 x 2h). Final exam (2h). Language of instruction: English.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Python and tools for research. Machine learning 1 or the equivalent. Probability 1 & 2. Statistics 1 & 2. Notions in optimization.

Maximum number of registrants

Remarks

Evaluations: - 1 written exam (20 min) (exam1) - 1 written exam (2h) (exam2) - 1 lab report (2h) (lab) Grade session 1: `Mark1 = 0.1 * exam1 + 0.45 * exam2 + 0.45 * lab` 2nd chance exam : 1 exam (2h) (exam3) if Mark1 < 10/20. Overall grade after 2nd chance exam : `Mark2 = 0.7 * Mark1 + 0.3 * exam3`

Course label :	Signal processing
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S2_SPR - Signal processing

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

• Usual signals ◦ Discrete and continuous signals, sampling, sensors ◦ Time series ◦ Images • The notion of representation ◦ Fourier transform, orthogonal bases / overcomplete representations ◦ Linear transforms in practice • Usual representations ◦ Global representations: FT, DFT, DCT ◦ STFT, Wavelets, Splines… ◦ Discrete cosines transform… • Sparse representations ◦ The notion of sparsity ◦ L1-penalty, LASSO… • Inverse problems in signal processing ◦ Denoising, Interpolation/inpainting ◦ Segmentation ◦ Filtering, smoothing

Educational goals

After successfully taking this course, a student should be able to: • Understand how to work with discrete representations of continuous signals • Manage usual changes of representation: Fourier, STFT, discrete cosines, splines, wavelets… • Choose an adequate representation depending on the data at hand • Solve data processing problems with continuous signals/functional data

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Exam, grading scale: (min) 0 – 20 (max) Labs, grading scale: (min) 0 – 20 (max) Average passing grade = 10/20

Online resources

Signal Processing & Linear Systems, B.P. Lathi 1998 Foundations of signal processing. Vetterli, Kovacevic & Goyal, 2014 A complete and recent overview of modern signal processing.

Pedagogy

24 hours, 7 lectures 5 exercises/labs Language of instruction is specified in the course offering information in the course and programme directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Bases of linear algebra, integration and functional analysis ; optimization Fundamental mathematics, Probability 1, Statistics 1, Python.

Maximum number of registrants

Remarks

Course label :	Data Challenge
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S2_DCA - Data Challenge

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

A short-term data challenge will be proposed to students (either by pairs or groups) over a short period of time (1 week) so that they can get familiar with the methodology of the participation to a Kaggle competition thanks to team collaboration. This project will be based on some datasets and will be supervised by a team of coaches/supervisors.

Educational goals

After successfully taking this course, a student should be able to: ● participate to a data challenge, ● handle brute datasets, ● give a presentation of his results and methods ● work in a team and collaborate with others.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Report + final presentation + score: grading scale: (min) 0 – 20 (max) Passing grade = 10/20

Online resources

Provided by the supervisors.

Pedagogy

Language of instruction is specified in the course offering information in the course and programme directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	0
Number of hours - Tutorial :	24
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

M1, S1

Maximum number of registrants

Remarks

Course label :	Seminars
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S2_SEM - Seminars

Education team

Teachers : Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Educational goals

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	0
Number of hours - Tutorial :	24
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Maximum number of registrants

Remarks

Course label :	Research project
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S2_RPR - Research project

Education team

Teachers : Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Educational goals

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	0
Number of hours - Tutorial :	24
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Maximum number of registrants

Remarks

Course label :	Internship
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S2_INT - Internship

Education team

Teachers :
External contributors (business, research, secondary education): various temporary teachers

Summary

Educational goals

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	0
Number of hours - Tutorial :	0
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Maximum number of registrants

Remarks

Course label :	English
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_ANG - Anglais

Education team

Teachers : Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Educational goals

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	0
Number of hours - Tutorial :	24
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Maximum number of registrants

Remarks

Course label :	FLE
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Madam HAKIMA LARABI / Madam VERONIQUE DZIWNIEL
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_FLE - FLE ou 2nde langue

Education team

Teachers : Madam HAKIMA LARABI / Madam VERONIQUE DZIWNIEL
External contributors (business, research, secondary education): various temporary teachers

Summary

Educational goals

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	0
Number of hours - Tutorial :	24
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Maximum number of registrants

Remarks

Course label :	LV2
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_LV2 - LV2 au choix

Education team

Teachers :
External contributors (business, research, secondary education): various temporary teachers

Summary

Educational goals

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	0
Number of hours - Tutorial :	24
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Maximum number of registrants

Remarks

Course label :	Algorithmics and databases 1 - Databases
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_AD1 - Algorithmics and databases 1 -

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

The course will go through the following topics: • logic syntax vs semantics • finite models and model checking • conjunctive queries • acyclic queries and Yannakakis algorithm • representation of query solutions by means of circuits • circuits and aggregation • fixedpoint logic and datalog • naive and semi-naive evaluation of datalog queries • supplementary magic set rewriting

Educational goals

The goal of this course is present theoretical foundations of databases. It presents the various connections with logic, optimizations of logical queries. Successful students attending this course will learn: • syntax and semantics of several logics • the algorithmics behind logical querying • various optimization methods for logical queries

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Labs, 4.0 credits, grading scale: A, B, C, D, E, F Exam, 2 credits, grading scale: A, B, C, D, E, F

Online resources

Serge Abiteboul, Richard B. Hull, Victor Vianu: Foundations of Databases. Addison-Wesley, 1995.

Pedagogy

24 hours, 8 lectures 4 exercises Language of instruction is specified in the course offering information in the course and programme directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Basic mathematical knowledge and basic knowledge in databases

Maximum number of registrants

Remarks

Course label :	Algorithmics and databases 2 - High Performance Computing
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_AD2 - Algorithmics and databases 2 -

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

This course aims at presenting the basics of parallel and high performance computing on one or multiple node(s) of multi-core CPUs and GPUs. This includes: · parallel architectures, · parallel algorithmics, · data and task parallelism, · data distribution and load balancing, · parallel programming on distributed-memory architectures (MPI standard), · sequential code optimization for high performance computing, · GPU programming and optimization

Educational goals

After successfully taking this course, a student should be able to: · know the various parallel architectures and the various parallel programming models, · design parallel algorithms, · design, implement and optimize parallel programs on high performance architectures (one or multiple node(s) of multi-core CPUs and GPUs), · determine whether an application is relevant for CPU and/or GPU parallel acceleration, · use a supercomputer with multiple CPU+GPU nodes.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Project, (min) 0 - 20 (max) Oral exam, (min) 0 - 20 (max) Passing grade 10/20

Online resources

• Parallel Programming in C with MPI and OpenMP, M.J. Quinn • U.C. Berkeley CS267 (J. Demmel et al.): http://www.cs.berkeley.edu/~demmel • Univ. Tennessee Knoxville CS 594 (J. Dongarra et al.): http://www.netlib.org/utk/people/JackDongarra/courses.htm • IDRIS course on MPI: http://www.idris.fr/formations/mpi/ • CUDA documentation (https://docs.nvidia.com/cuda/index.html) and courses (https://developer.nvidia.com/educators/existing-courses)

Pedagogy

24 hours, 6 lectures, 6 labs/tutorial sessions English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

C or Python programming

Maximum number of registrants

Remarks

Course label :	Algorithmics and databases 3
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_AD3 - Algorithmics and databases 3

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Educational goals

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Maximum number of registrants

Remarks

Course label :	Refresher in computer science
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_RCS - Refresher in computer science

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Fundamentals of object oriented programming, with a strong focus on the Python programming language. This course emphasizes the theoretical fundamentals of object oriented programming with hands-on training for rapidly prototyping applications. The practicals will illustrate : ● the benefits of object oriented programming, ● the ability of Python to quickly translate ideas into code, ● the process of developing and scaling a proof-of-concept, and preparing for production. Some of the frameworks and tools we will utilize are : ● pyTest, cProfile, pycallgraph, Pylint, Travis, asyncio, zeroMQ, Docker, Flask.

Educational goals

After successfully taking this course, a student should: ● understand the notions of class and object, ● understand the concepts of encapsulation and inheritance, ● understand the most common design patterns used in object oriented programming, ● understand the principle of inversion-of-control through dependency injection, ● lay the groundwork for testing, analyzing and profiling software, ● learn to leverage continuous integration in the development process, ● learn to package and prepare an application for production, ● learn to scale applications through asynchronous parallelization, ● learn to quickly prototype applications with simple web frontends.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Labs, grading scale: (min) 0 – 20 (max) Exam, grading scale: (min) 0 – 20 (max)

Online resources

Design Patterns: Elements of Reusable Object-Oriented Software. Erich Gamma, Richard Helm, Ralph Johnson, John Vlissides. Python Programming: An Introduction to Computer Science. John Zelle. Clean Code: A Handbook of Agile Software Craftsmanship. Robert C. Martin Series. Flask Web Development: Developing Web Applications with Python. Miguel Grinberg. Continuous Delivery: Reliable Software Releases through Build, Test, and Deployment Automation. Jez Humble, David Farley.

Pedagogy

Language of instruction is specified in the course offering information in the course and programme directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Basics of programming in Python.

Maximum number of registrants

Remarks

Course label :	Refresher in mathematics
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_RMA - Refresher in mathematics

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Reminders on linear algebra and applications: Discrete Fourier Transform, Singular Value Decomposition, linear regression, low rank approximations. Basics on optimization with constraints. Lagrange multipliers. Uzawa algorithm.

Educational goals

After successfully taking this course, a student should be familiar with fundamental concepts from linear algebra and nonlinear optimization which are relevant to data science.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Exam1, (min) 0 - 20 (max) Exam2, (min) 0 - 20 (max) Passing grade 10/20

Online resources

Gene H Golub and Charles F Van Loan. Matrix computations. JHU press, 2013.

Pedagogy

24 hours, 12 hours lectures, 12 hours exercise session.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Basic mathematical knowledge

Maximum number of registrants

Remarks

Course label :	Theoretical foundations of machine learning 1 - Bayesian Learning
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_TF1 - Theoretical foundations of mac

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

· Probabilistic modeling and parameter inference as the main learning task · Bayesian decision theory · Refresher on MCMC · Variational inference · Gaussian processes, and their application to regression · Bayesian optimization, with application to hyperparameter tuning · Bayesian neural networks

Educational goals

After successfully taking this course, students should be able to: · Understand the philosophy of the Bayesian framework, and how it can be used to make decisions under uncertainty · Design probabilistic models for the task at-hand · Run some computational tools for Bayesian inference, either MCMC or variational inference · Know about the limitations of those approaches, and be knowledgeable about topical research questions

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Labs (60% of the grade) : (min) 0 - 20 (max) Final exam (40% of the grade) : (min) 0 - 20 (max) Passing grade 10/20

Online resources

Probabilistic Machine Learning: Advanced Topics, Kevin Murphy (2023) Bayesian Reasoning and Machine Learning, David Barber (2012) Pattern Recognition and Machine Learning, Christopher Bishop (2006) The Bayesian Choice, Christian Robert (2007)

Pedagogy

24 hours, which include 4 labs and a final exam

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

From the M1 year : Statistics 2, Models for Machine Learning

Maximum number of registrants

Remarks

Course label :	Theoretical foundations of machine learning 3
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_TF3 - Theoretical foundations of mac

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

-

Educational goals

-

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

-

Maximum number of registrants

Remarks

Course label :	Theory of Machine Learning
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_TF2 - Theoretical foundations of mac

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

● The problem of sequential decision making under uncertainty ● Markov decision problems ● the planning problem, and algorithms ● the reinforcement learning problem, and algorithms (incl. deep reinforcement learning) ● the bandit problem, and algorithms All notions visited during the course are investigated in practical sessions. Course details can be found in: https://debabrota-basu.github.io/course_bandit_rl.html

Educational goals

After successfully taking this course, a student should be: ● know what the problem of sequential decision making under uncertainty is ● know the various approaches to solve, along with the associated hypothesis ● know how to recognize such a problem, and model it accordingly ● know Markov decision problems, and related problems ● know about the main planning algorithms to solve them ● know about reinforcement learning approaches ● know the bandit problem, and the main algorithms

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Labs, 1.5 credits, grading scale: (min) 0 – 20 (max) - Passing grade = 10/20 Exam, 1.5 credits, grading scale: (min) 0 – 20 (max) - Passing grade = 10/20

Online resources

Bertsekas, Dynamic programming and optimal control, MIT Press Bertsekas, Neurodynamic Programming, MIT Press Puterman, Markov decision processes, Wiley Sutton, Barto, Reinforcement Learning, MIT Press, 2nd edition Tor Lattimore and Csaba Szepesvari, Bandit Algorithms, Cambridge University Press

Pedagogy

24 hours, 12h lectures, 12h labs/tutorial sessions

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

The M1 program + Machine learning 3M1 Data science.

Maximum number of registrants

Remarks

Course label :	Advanced Machine Learning 1 - Natural Learning Processing
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_AM1 - Advanced machine learning 1

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

NLP: definition, applications, evaluation, brief history NLP pipeline: tokenization, symbolic and neural processing Language modeling Embeddings/RNN/Attention/Transformers Unsupervised learning, scaling, transfer, and training stages (RLHF) Text encoding, efficiency issues, multimodality Agents, tool use, RAG Privacy, fairness, multilinguality, data annotation

Educational goals

After successfully taking this course, a student should be able to: Roughly understand and apply modern NLP models

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Project (min) 0 - 20 (max) Knowledge Exam (min) – 0 – 20 (max) Paper presentation, (min) 0 - 20 (max) Passing grade 10/20

Online resources

Introduction to Natural Language Processing By Jacob Eisenstein

Pedagogy

English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Preferably: machine learning and basic computer science, Python

Maximum number of registrants

Remarks

Course label :	Advanced Machine Learning 2 - Machine Learning for Signal Processing
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_AM2 - Advanced machine learning 2

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Applications of machine learning techniques to statistical signal processing, with a focus on inverse problems. Methods and notions covered are summarized below: - definition of an inverse problem (Bayesian formulation and estimators, sparse regularization, quality assessment in signal and image processing) - sparsity and compressed sensing - adaptive representations: parametric/non parametric, dictionary learning - refreshers in (convex) optimization (duality, proximal operator, Legendre-Fenchel conjugate function, 1st and 2nd proximal theorems) - splitting methods in optimization: application with the ADMM and PnP-ADMM algorithms - splitting approaches for MCMC (AXDA, SGS, PnP-SGS)

Educational goals

After successfully taking this course, a student should have a minimum culture about signal processing problems that can be tackled using machine learning: - learning of representations compared to using mathematical functions (e.g., wavelets), - importance of sparsity, - source separation, pattern recognition, segmentation, - propose an adapted model, - implement some approaches, deterministic/probabilistic - critically evaluate the methods’ applicability in usual contexts, After successfully taking this course, a student should be able to: - understand the methodological connections between models in machine learning and in statistical signal processing; - identify relevant machine learning models and techniques for statistical signal processing applications; - understand representative algorithms at the interface between machine learning and standard statistical signal processing (PnP optimization algorithm, SPA Gibbs sampler, PnP MCMC); - implement representative algorithms to solve some inverse problems arising in statistical signal processing.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Continuous evaluation, based on: - lab report(s), 50% of the overall grade, grading scale: (min) 0 – 20 (max) - exams, 50% of the overall grade, grading scale: (min) 0 – 20 (max) 2nd chance exam (session 2): - grade on 20 points - final grade for the course: 50% session 1 (grade at the continuous assessment), 50% session 2

Online resources

- Murphy, K. P. (2012). Machine learning: a probabilistic perspective. MIT press. - Beck, A. (2017). First-Order Methods in Optimization. Society for Industrial and Applied Mathematics press.

Pedagogy

- Lectures (6x2h), labs (4x2h) and tutorial sessions (2x2h). - Exams: 2x1h. - Language of instruction is specified in the course offering information in the course and programme directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Lectures from the M1 Data Science programme (or equivalent): Python and tools for research. Machine learning 1 or the equivalent. Probability 1 & 2. Statistics 1 & 2. Signal processing. Models for machine learning. Notions in optimization.

Maximum number of registrants

Remarks

Labs, grading scale: (min) 0 – 20 (max) Exam, grading scale: (min) 0 – 20 (max) Average passing grade = 10/20 A 2nd chance exam is proposed if the overall grade for session 1 (continuous assessment) is lower than 10/20.

Course label :	Advanced Machine Learning 3 - Fairness in Thrustworthy Machine Learning
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_AM3 - Advanced machine learning 3

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Nowadays, machine learning methods find widespread application due to their ability to learn models that per-form outstandingly, sometimes reaching human-level capabilities. However, if these models have the potential to impact human lives, for example in justice, solely evaluating them in terms of accuracy is not sufficient any-more. Other notions then need to be considered to ensure that the models are trustworthy and that they do not have a negative impact on individuals. This course will focus on fairness as a trustworthiness concept that aims to eliminate discrimination in machine learning models. First, we will recognize various sources of unfairness before exploring several of the numerous fairness metrics proposed in literature. Then, focusing on a family of measures, we will study several strategies to mitigate these discriminatory behaviors. Finally, we will examine how privacy, another important aspect of trustworthiness, can affect fairness.24 hours, 6 lectures, 6 practical sessions.

Educational goals

The goal of this course is to provide an introduction to the problem of fair machine learning, a core concept for building more trustworthy systems. After successfully completing this course, a student should: • Be able to identify machine learning problems where fairness issues may arise. • Be able to evaluate the degree of unfairness of the models with various metrics. • Be able to deploy some existing solutions to mitigate the discriminatory behaviors. • Be aware of the potential impact that privacy may have on fairness.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Practicals, (min) 0 - 20 (max) Written exam, (min) 0 - 20 (max) Passing grade 10/20

Online resources

• "Fairness and Machine Learning: Limitations and Opportunities", Solon Barocas, Moritz hardt, Arvind Narayanan • "The Algorithmic Foundations of Differential Privacy", Cynthia Dwork, Aaron Roth

Pedagogy

24 hours, 6 lectures, 6 practical sessions. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

• Basic notions of probabilities and statistics • Basic notions of linear algebra • Core concepts in machine learning (e.g. supervised learning, empirical risk minimization, gradient de-scent, …) • Python programming (e.g. jupyter notebook, numpy, pandas, scikit-learn, ...)

Maximum number of registrants

Remarks

Course label :	Advanced Machine Learning 4 - Computer Vision
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_AM4 - Advanced machine learning 4

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

• Image processing • Keypoints and Landmarks • Object classification and detection • Optical Flow – foundation and principles + deep learning approaches • Unsupervised Visual Feature Learning

Educational goals

After successfully taking this course, a student should be able to: · Understand the properties of visual data and the challenges associated to it · Master some fundamental tools in computer vision · Identify computer vision problems and leverage the right tools to solve them · Address current computer vision problems by employing state-of-the-art solutions

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Labs, (min) 0 - 20 (max) Exam, (min) 0 - 20 (max) Passing grade 10/20

Online resources

R. Szeliski - Computer Vision: Algorithms and Applications, Springer 2010 R. Szeliski - Computer Vision: Algorithms and Applications – 2nd edition, Springer 2022

Pedagogy

24 hours, 12 lectures, 12 labs/tutorial sessions English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Machine Learning courses from M1 Data Science Signal Processing course from M1 Data Science

Maximum number of registrants

Remarks

Course label :	Advanced machine learning 5
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_AM5 - Advanced machine learning 5

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Educational goals

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Maximum number of registrants

Remarks

Course label :	Advanced machine learning 6
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S3_AM6 - Advanced machine learning 6

Education team

Teachers :
External contributors (business, research, secondary education): various temporary teachers

Summary

Educational goals

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Maximum number of registrants

Remarks

Course label :	Ethics and digital law
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S4_EDL - Ethics and digital law

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

• Ethics and right of data, complementarity or competition? The place of codes of conduct and certification. • Personal data : notion and sources of notion and sources of regulation • Non personal data and public data : notions and sources of regulation • The person concerned by data processing, the person responsible for data processing • Main principles of RGPD (european regulation) • Legal causes of data processing: agreement and consent • Legal causes of data processing: the legitimate interest in collecting data • Rights and obligations of the person concerned by data • Rights and obligations of the person responsible for data processing • Transfer of personal data toward other countries or international organisations • The delegate to data protection • The french CNIL, the european committee for data protection, the european

Educational goals

The goal of this course is to give students insights in the main aspects of right and ethics as far as data analysis is concerned.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Exam, grading scale: (min) 0 – 20 (max) - Passing grade = 10/20

Online resources

Pedagogy

24 hours, 12 lectures. Language of instruction is specified in the course offering information in the course and program directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	12
Number of hours - Tutorial :	12
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

None.

Maximum number of registrants

Remarks

Course label :	Reading group
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S4_RGR - Reading group

Education team

Teachers : Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Educational goals

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	0
Number of hours - Tutorial :	24
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Maximum number of registrants

Remarks

Course label :	Seminars
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S4_SEM - Seminars

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Each seminar will focus on a specific topic in data science, presented by a researcher or industry expert.

Educational goals

After successfully taking this course, a student will have a basic knowledge on various topics in data science (current research topic, a team’s research theme, some application of ML/DS in the industry,... )

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: A 3-5 pages presenting a seminar with a personal analysis and a bibliography on the subject Passing grade 10/20

Online resources

Pedagogy

24 hours, 12 sessions

Sequencing / learning methods

Number of hours - Lectures :	0
Number of hours - Tutorial :	24
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Basic knowledge in maths, computer science and data science.

Maximum number of registrants

Remarks

Course label :	Internship and memoir
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S4_IME - Internship and memoir

Education team

Teachers : Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Educational goals

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	0
Number of hours - Tutorial :	0
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Maximum number of registrants

Remarks

Course label :	Data challenge
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S4_DCH - Data challenge

Education team

Teachers : Mister PIERRE-ANTOINE THOUVENIN / Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

A short-term data challenge will be proposed to students (either by pairs or groups) over a short period of time (up to 3 to 4 weeks) so that they can get familiar with the methodology of the participation to a Kaggle competition thanks to team collaboration. This project will be based on some datasets and will be supervised by a team of coaches/supervisors.

Educational goals

After successfully taking this course, a student should be able to: ● participate to a data challenge, ● handle brute datasets, ● give a presentation of his results and methods ● work in a team and collaborate with others.

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments: Report + final presentation + score: grading scale: (min) 0 – 20 (max) Passing grade = 10/20

Online resources

Articles from the literature provided by the supervisor.

Pedagogy

Language of instruction is specified in the course offering information in the course and programme directory. English is the default language.

Sequencing / learning methods

Number of hours - Lectures :	0
Number of hours - Tutorial :	24
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

M1 Data science

Maximum number of registrants

Remarks

Course label :	Research project
Teaching departement :	EEA / Electrotechnics - Electronics - Control Systems
Teaching manager :	Mister PIERRE CHAINAIS
Education language :
Potential ects :	0
Results grid :
Code and label (hp) :	MR_DS_S4_RPR - Research project

Education team

Teachers : Mister PIERRE CHAINAIS
External contributors (business, research, secondary education): various temporary teachers

Summary

Educational goals

Sustainable development goals

Knowledge control procedures

Continuous Assessment
Comments:

Online resources

Pedagogy

Sequencing / learning methods

Number of hours - Lectures :	0
Number of hours - Tutorial :	24
Number of hours - Practical work :	0
Number of hours - Seminar :	0
Number of hours - Half-group seminar :	0
Number of student hours in TEA (Autonomous learning) :	0
Number of student hours in TNE (Non-supervised activities) :	0
Number of hours in CB (Fixed exams) :	0
Number of student hours in PER (Personal work) :	0
Number of hours - Projects :	0

Prerequisites

Maximum number of registrants

Remarks