Classes
You may use this guide to choose your UE (Unité d'Enseignement), whether you are a student of the [AI] parcourse or another parcouse of the Informatics master. All the [AI] UE are open to other parcourses. However, make sure that you have appropriate PREREQUISITES. In doubt, ask the instructors or contact the Coordinator of the AI master program. You may also catch up during the summer by following on-line CRASH COURSES.
FOR STUDENT HAVING ACCESS TO ECAMPUS, you can check the:
M1 classes on Ecampus (from 2020/2021)
M2 classes on Ecampus (from 2020/2021)
M1 [AI] classes
Refresher classes
PREparatory classes, 2.5 ECTS each. Mandatory for all M1 [AI] students, except PRE3.
Prerequisites for M2 students who want to follow M2 [AI] classes.
If you cannot take them, study on your own online CRASH COURSES.
PRE1: APPLIED STATISTICS - online class, website. - Statistiques appliquées
PRE2: MATHEMATICS FOR DATA SCIENCE (details) -online-class, website- Mathématiques pour les sciences des données
PRE3: RELATIONAL DATABASES ecampus page (details from last year) - Bases de données relationnelles, SQL
PRE4: SCIENTIFIC PROGRAMMING (syllabus) -online-class, website- Programmation scientifique en Python
Foundational classes
Tronc commun (TC) “classic classes", 2,5 ECTS each.
To get a consistent path of study with adequate prerequisites, among optional classes, always take either green (ML path) or brown (NLP path) classes (or both).
TC0: Foundational Principles of Machine Learning (FPML, organization, all material here) - [ecampus: TBA].- Introduction to Machine Learning -- with PRE1 and PRE2 as prerequisites, and PRE4 is strongly recommended. Note that PRE1 and PRE2 are mandatory, i.e., you must attend them to be allowed to follow TC0/FPML, except if you can argue that you are already very fluent in statistics (PRE1) and linear algebra (PRE2). This class (or an equivalent) is a prerequisite for almost all other [AI] classes.
TC1: Machine Learning Algorithms - [external site][ecampus]. - Algorithmes d'apprentissage -- with TC0 as prerequisite. This class is a prerequisite for OPT4 (DL).
TC2: OPTIMIZATION -- website 2021/2022 - Optimisation, descente de gradient, etc. -- with PRE2 as prerequisite
TC3: INFORMATION RETRIEVAL (website from previous year)-[ecampus].- Recherche et extraction d’information dans les textes -- with PRE1, 2, and OPT17 "Hands-on NLP" as prerequisite.
TC6: Large-Scale Distributed Data Processing (website from last year) -- Algorithmes distribués et bases de données -- with PRE3 as prerequisite (or good knowledge of database knowledge systems, at least of SQL).
Growth classes
Formerly all OPTional classes, though some in bold, are now mandatory for the [AI] track :-) 2.5 ECTS each.
OPT4: DEEP LEARNING -- With TC1 as prerequisite. Highly recommended for all, mandatory for all [AI] students.
OPT8: HISTORY OF AI [ecampus]
OPT9: Hands-on Machine Learning (details)[external site][ecampus]. participate to a challenge -- With PRE1 and PRE2 as prerequisite.
OPT13: INFORMATION THEORY (website from a previous similar class). Théorie de l'information -- With PRE1 as prerequisite
OPT 15: Fairness in AI: New class. Syllabus. With PRE1 as prerequisites. Recommended to be taken jointly with OPT 16.
OPT 16: Creation of a challenge in Artificial Intelligence (Website from previous years) [ecampus].: Create a challenge (that other students will solve as a TER project). Team work in teams of 5-6 people. -- With TC0 and PRE4 (or equivalent) as prerequisite.
OPT 17: Hands-on Natural Language Processing [external site]. New class to learn how to manipulate large text corpora.
Projects and practical experiences
Summer school (école thématique)
Internship (stage)
TER: Travail d'Etude et de Recherche (small internship). Personal work supervised by a member of the master's teaching team or in s university research lab. This work can take the form of a state of the art on a given scientific subject and / or the implementation of state algorithms for application on a given problem. This work is normally not remunerated However, If an internship is longer than 2 months it must be remunerated.
Other "soft" skills
Languages: French or English for non-native speakers.
I&E: Innovation and Entrepreneurship.
FVE: Research and Development training, mutualised with avec MIAGE d'Orsay. Formation à la Vie en Entreprise
Teacher responsible for I&E basics/BDlabs (M1 EIT) is: Guillaume DION
M2 [AI] classes
Foundational classes
Tronc commun (TC) “classic classes", mandatory for all [AI] students, 2,5 ECTS each.
TC4: PROBABILISTIC GENERATIVE MODELS (website from last year) (NEW website 2020/2021)-online-class, website- HMMs etc. -- with PRE1 and 2 as prerequisite
TC5: SIGNAL PROCESSING (Website from last year) -online-class, website- Traitement du signal -- with PRE2 and 4 as prerequisite
Growth classes
Formerly all OPTional classes, though some are now mandatory :-) 2.5 ECTS each.
green (ML path) indicates Machine Learning of Computer Vision classes or brown (NLP path) indicate Natural Language Processing classes.
OPT1: GRAPHICAL MODELS (details) (website from previous year) [ecampus]. Modèles graphiques pour l’accès à l'information à grande échelle -- With TC4 as prerequisite
OPT2: COMPUTER VISION (website from last year) New class, syllabus -- With TC1 and OPT4 as prerequisite.
OPT3: REINFORCEMENT LEARNING (overleaf) [OLD external site][ecampus]. Apprentissage par renforcement -- With TC1 as prerequisite.
OPT5: AUTOMATIC SPEECH RECOGNITION AND NATURAL LANGUAGE PROCESSING [external site][ecampus].
OPT6: LEARNING THEORY AND ADVANCED MACHINE LEARNING [external site] [ecampus]. Apprentissage avancé et théorie -- With TC1 as prerequisite
OPT7: ADVANCED OPTIMIZATION AND AUTOMATED MACHINE LEARNING [external site][ecampus] (Formely Optimisation avancée,) -- With TC2 as prerequisite
OPT 10: IMAGE MINING -- With PRE1, 2, and 4, as prerequisites.
OPT 11: DEEP LEARNING FOR NLP (website from previous year) [external site][ecampus]. Natural Language Processing -- With OPT4 as prerequisite.
OPT 12: TEXT MINING AND CHATBOTS -- [external site][ecampus]- With TC3 and 6 as prerequisite.
OPT 14: MULTILINGUAL NATURAL LANGUAGE PROCESSING (details) [external site][ecampus] -- With TC4 as prerequisite.
Soft skills
Communitation
I&E: Innovation and Entrepreneurship.
Conferences
Teacher responsible for I&E Study (M2 EIT ) is: Alvaro PINA STRANGER
Internships
5 to 6 month internship in a research lab or a company (Coordination: Marc Evrard and Thomas Gerald).