Machine learning

  • Enseignement


    Faculté Faculté des sciences et de médecine
    Domaine Informatique
    Code UE-SIN.08022
    Langues Anglais
    Type d'enseignement Cours
    Cursus Master
    Semestre(s) SP-2021


    Français Apprentissage automatique
    Allemand Maschinelles Lernen
    Anglais Machine learning

    Horaires et salles

    Horaire résumé Lundi 14:15 - 17:00, Hebdomadaire
    Struct. des horaires 2h +2h par semaine durant 14 semaines
    Heures de contact 56



    The goal of this course is to understand the foundation of Machine Learning as a field, providing the basis to master its many branches and applications. After an introduction about how machines learn, the focus will be on a short selection of key algorithms for supervised, unsupervised and reinforcement learning. The students will learn how parametrized function approximators can be used to take decisions, how to update their parametrization to modify their behavior, and how to leverage data and interactions in real-world applications.

    The course is composed of theoretical lectures, explaining the inner working and intuitions behind the methods, interleaved with practical sessions to gain hands-on experience. The students will be introduced to both re-implementing (and customizing) some of the basic algorithms, and to applying the current standard libraries on practical applications.
    The theoretical requirements include a basic understanding of linear algebra, calculus and statistic, as far as appropriate to understand the algorithms' inner workings. The practical sessions require a degree of familiarity with the Python programming language, and a working installation for the exercises. All lectures and material will be in English.

    Objectifs de formation

    This course is set to provide a fundamental understanding of what is Machine Learning and how all of its methods operate, with practical experience on selected algorithms and libraries. The core objective is to support and facilitate further learning on the topic, both in the form of further self-study and as an introduction for advanced classes available in the Masters course.

    Conditions d'accès

    Please register to the course on the students portal < >; in case of problems write an email with your name, Nr SIUS, Code and Course Name to Stephanie Fasel < >.
    All official communication will go through Moodle, please register at your earliest convenience < >. All lectures will be online for the time being, using Microsoft Teams: access details will be made available on Moodle.


    Cours Master SES

    Les unités d’enseignement se composent généralement de deux heures de cours et deux heures d’exercices par semaine. Nous vous prions de bien vouloir vous conformer aux délais d’inscriptions aux épreuves de la Faculté des sciences et de médecine.

    Hors domaine



    - Y. Abu-Mostafa, M. Magdon-Ismail, L. Hsuan-Tien. Learning from Data. AMLBook.
    - M. Bishop. Pattern Recognition and Machine Learning. Springer.
    - I. Goodfellow, Y. Bengio, A. Courville. Deep Learning. MIT Press.
    - R. Sutton, A. Barto. Reinforcement Learning. MIT Press.

  • Dates et salles
    Date Heure Type d'enseignement Lieu
    22.02.2021 14:15 - 17:00 Cours PER 21, salle C230
    01.03.2021 14:15 - 17:00 Cours PER 21, salle C230
    08.03.2021 14:15 - 17:00 Cours PER 21, salle C230
    15.03.2021 14:15 - 17:00 Cours PER 21, salle C230
    22.03.2021 14:15 - 17:00 Cours PER 21, salle C230
    29.03.2021 14:15 - 17:00 Cours PER 21, salle C230
    12.04.2021 14:15 - 17:00 Cours PER 21, salle C230
    19.04.2021 14:15 - 17:00 Cours PER 21, salle C230
    26.04.2021 14:15 - 17:00 Cours PER 21, salle C230
    03.05.2021 14:15 - 17:00 Cours PER 21, salle C230
    10.05.2021 14:15 - 17:00 Cours PER 21, salle C230
    17.05.2021 14:15 - 17:00 Cours PER 21, salle C230
    31.05.2021 14:15 - 17:00 Cours PER 21, salle C230
  • Modalités d'évaluation

    Examen écrit - SP-2021, Session d'été 2021

    Date 24.06.2021 14:00 - 16:00
    Mode d'évaluation Par note

    Examen écrit en présence / 120 minutes / open book

  • Affiliation
    Valable pour les plans d'études suivants:
    Complément au doctorat (Faculté des sciences) [PRE-DOC]
    Version: 2020_1/v_01
    Complément au doctorat ( Faculté des sciences et de médecine) > UE de spécialisation en Informatique (niveau master)

    Data Analytics & Economics 90 [MA]
    Version: 2020/SA-v01
    Courses min 63 ECTS > Mandatory Modules (45 to 63 ECTS) > Module I: Data Analytics (Data)

    Economie politique 90 [MA]
    Version: 2021/SA_V02
    Information pour l'étudiant (à définir) > Economie quantitative > 369 - Option : "Economie quantitative"

    Enseignement complémentaire en sciences
    Version: ens_compl_sciences
    Paquet indépendant des branches > UE de spécialisation en Informatique (niveau master)

    Informatique [3e cycle]
    Version: 2015_1/V_01
    Complément aux études doctorales en informatique > UE de spécialisation en Informatique (niveau master)

    MSc en informatique (BeNeFri)
    Version: 2010_2/V_02
    MSc en informatique (BeNeFri), cours, séminaires et travail de Master > UE de spécialisation en Informatique (niveau master)