What's happening at Sorbonne University

See all

Discover our news, events, portraits, videos, publications and more.

Education

Our Academic Programs

In Arts and Humanities, Medicine, and Science and Engineering

Choosing Sorbonne University means joining a world-renowned higher education and research institution. By joining our community of 55,000 students and 360,000 alumni worldwide, you'll be giving your all to a rigorous academic program and receiving the best in multidisciplinary teaching. 

Information for International Students

Are you a current or prospective international student? 

Whether studying on exchange or seeking a full degree at Sorbonne University, access essential contact information, resources for learning French and a glimpse into student life. 

Research and Innovation

Sorbonne University promotes excellence at the core of each of its disciplines and develops numerous interdisciplinary programs capable of meeting the major challenges of the 21st century.

Study at | Sorbonne University

Participate in the great adventure of learning, succeed in high-level studies and prepare to create the future.

Parismus is the international student association of Sorbonne University

Parismus

Parismus is the international student association of Sorbonne University.

Bringing together 10 institutions that offer studies in literature, medicine, science, engineering, technology and management, our alliance fosters a global approach to teaching and research, promoting access to knowledge for all.

Alliance 4EU+

The 4EU+ Alliance

In a changing world, Sorbonne University has joined forces with six universities: Charles University in Prague, the University of Warsaw, Heidelberg University, the University of Milan, the University of Geneva and the University of Copenhagen to create the 4EU+ Alliance.

With an innovative model of the European university, seven large research-intensive universities are working together to respond to the educational and research challenges facing Europe today.

Les Alliances de Sorbonne Université

How to get prepared for the new academic year 2023-2024

Discover our step-by-step guide to get ready for the start of the new academic year. Learn everything there is to know from the application process to the beginning of the first term.

Préparer ma rentrée slider


Publications

All publications

Artisans Abroad

Par Fabrice Bensimon

British Migrant Workers in Industrialising Europe, 1815-1870

Graduate

25 000

students

193

bachelor degrees

192

master degrees

13

campuses

Courses

Discover our courses catalog

Medicine

The Faculty of Medicine teaches the 3 cycles of medical studies: from PASS (integrated into the faculty) to the 3rd cycle including DES, DESC, DU and DIU. The lessons are given mainly on two sites: Pitié-Salpêtrière and Saint-Antoine. The faculty also provides paramedical education: speech therapy, psychomotricity and orthoptics. The Saint-Antoine site includes a midwifery school.

Study | at the faculty of medicine

One of our riches is the diversity of students and their backgrounds. Sorbonne University is committed to the success of each of its students and offers them a wide range of training as well as support adapted to their profile and their project.

Associative life

One of our riches is the diversity of students and their backgrounds. Sorbonne University is committed to the success of each of its students.

21 393

users

17 527

students

715

Doctors in medecine and research

12

Research centers

Chiffres-clés

Master 2 in Mathematics - Learning and Algorithms track

The Master 2 Learning and Algorithms track (M2A) offers a dual training in Mathematics and Computer Science, focusing on data science and artificial intelligence, with a particular emphasis on statistical learning and deep learning. The training provided is both :

  • theoretical, through teaching consisting of lectures, tutorials, practical work and projects
  • operational, thanks to an internship in the second semester, and through direct contact with companies and laboratories proposing concrete machine learning problems.
Master 2 in Mathematics - Learning and Algorithms track

Courses Taught in English - Master 2 in Mathematics - 2A

2nd year Master - 1st Semester - 3 ECTS - English Level: Scientific English (no test required)


Brief Description

This course presents convergence results for many sequential algorithms of Machine Learning, both in the deterministic and random setting. It will be shown that sequential learning provides adaptive and robust solutions to many convex optimization problems, with and without constraints. Convergence of algorithms will be illustrated with R and Python on the MNIST dataset.


Prerequisites

Fundamentals of probability and statistics, scientific computation in Python or R.


Contact

Olivier Wintenberger (olivier.wintenberger@sorbonne-universite.fr)

2nd year Master - 2nd Semester - 3 ECTS - English Level: Scientific English (no test required)


Brief Description

This course presents how to use neural networks for adaptive numerical approximation.
Topics covered:

  1. Functions that can be represented by neural networks
  2. Elementary proofs of Cybenko's theorem
  3. The Takagi function
  4. Construction of datasets and curse of dimension
  5. Interpretation of stochastic gradient algorithms in the form of ordinary differential equations
  6. Applications to problems from scientific computing for CFD in relation with image classification

Illustration with some software.


Prerequisites

Fundamentals of analysis and interest in programming.


Contact

Bruno Desprès (bruno.despres@sorbonne-universite.fr)

2nd year Master - 2nd Semester - 3 ECTS - English Level: Scientific English (no test required)


Brief Description

The goal of this course is twofold: on the one hand, to discover the real challenges of basic biology and medicine where statistical learning is already successfully used; on the other hand, to acquire the basics for modeling complex medical data.


Prerequisites

Fundamentals of probability and statistics, linear algebra, Python.


Contact

Xavier Tannier (xavier.tannier@sorbonne-universite.fr)

2nd year Master - 2nd Semester - 1,5 ECTS - English Level: Scientific English (no test required)


Brief Description

This lecture provides an overview of PAC-Bayesian theory, starting from statistical learning theory (generalization bounds and oracle inequalities) and covering algorithmic developments by variational inference, up to recent PAC-Bayesian analyses of generalization properties of deep neural networks.


Prerequisites

Fundamentals of probability and statistics.


Contact

Badr-Eddine Chérief-Abdellatif (badr-eddine.cherief-abdellatif@sorbonne-universite.fr)

2nd year Master - 2nd Semester - 3 ECTS - English Level: Scientific English (no test required)


Brief Description

The objective of this course is twofold: to illustrate the processing of high-dimensional data when data is missing (through the prism of compressed acquisition and matrix completion), and to acquire the basics of convex optimization. These two topics, which will be addressed in concert as they are closely related, open the way to many other statistical learning domains and problems encountered in data science.


Prerequisites

Fundamentals of probability and statistics, linear algebra, Python.


Contact

Claire Boyer (claire.boyer@sorbonne-universite.fr)

2nd year Master - 2nd Semester - 3 ECTS - English Level: Scientific English (no test required)


Brief Description

This course will attempt to provide an overview of the latest mathematical trends in the machine learning and statistical learning community.

Topics covered:

  1. Approximation theory for neural networks
  2. VC dimension for neural networks
  3. Minimal bounds for regression with neural networks
  4. GANs
  5. Implicit bias in gradient descent
  6. Interpolation & benign overfitting
  7. Privacy

Prerequisites

Fundamentals of probability and statistics, linear algebra.


Contact

Eddie Aamari (eddie.aamari@sorbonne-universite.fr)

2nd year Master - 2nd Semester - 3 ECTS - English Level: Scientific English (no test required)


Brief Description

Data can often be represented by point clouds in high-dimensional spaces. In practice, it is found that these points are not uniformly distributed in the surrounding space: they are located near non-linear structures of smaller dimension, such as curves or surfaces, which are interesting to understand. Geometric inference, also called topological data analysis, is a recent field consisting in the study of statistical aspects associated with the geometry of data. This course aims to provide an introduction to this rapidly growing field.


Prerequisites

Fundamentals of probability and statistics.


Contact

Eddie Aamari (eddie.aamari@sorbonne-universite.fr)