Machine learning

  • Teaching

    Details

    Faculty Faculty of Science and Medicine
    Domain Computer Science
    Code UE-SIN.06022
    Languages English
    Type of lesson Lecture
    Level Bachelor
    Semester SP-2020

    Title

    French Apprentissage automatique
    German Maschinelles Lernen
    English Machine learning

    Schedules and rooms

    Summary schedule Monday 14:15 - 17:00, Hebdomadaire, PER 21, Room C230
    Struct. of the schedule 2+2h par semaine durant 14 semaines
    Contact's hours 56

    Teaching

    Responsibles
    Teachers
    Description

    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.

     

    Training objectives

    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.

    Comments

    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.

    Softskills
    No
    Off field
    No
    BeNeFri
    Yes
    Mobility
    Yes
    UniPop
    No

    Documents

    Bibliography

    - Y. Abu-Mostafa, M. Magdon-Ismail, L. Hsuan-Tien. Learning from Data. AMLBook.
      http://amlbook.com/
    - M. Bishop. Pattern Recognition and Machine Learning. Springer.
      https://www.springer.com/gp/book/9780387310732
    - I. Goodfellow, Y. Bengio, A. Courville. Deep Learning. MIT Press.
      https://www.deeplearningbook.org/
    - R. Sutton, A. Barto. Reinforcement Learning. MIT Press.
    https://mitpress.mit.edu/books/reinforcement-learning-second-edition

  • Dates and rooms
    Date Hour Type of lesson Place
    17.02.2020 14:15 - 17:00 Cours PER 21, Room C230
    24.02.2020 14:15 - 17:00 Cours PER 21, Room C230
    02.03.2020 14:15 - 17:00 Cours PER 21, Room C230
    09.03.2020 14:15 - 17:00 Cours PER 21, Room C230
    16.03.2020 14:15 - 17:00 Cours PER 21, Room C230
    23.03.2020 14:15 - 17:00 Cours PER 21, Room C230
    30.03.2020 14:15 - 17:00 Cours PER 21, Room C230
    06.04.2020 14:15 - 17:00 Cours PER 21, Room C230
    20.04.2020 14:15 - 17:00 Cours PER 21, Room C230
    27.04.2020 14:15 - 17:00 Cours PER 21, Room C230
    04.05.2020 14:15 - 17:00 Cours PER 21, Room C230
    11.05.2020 14:15 - 17:00 Cours PER 21, Room C230
    18.05.2020 14:15 - 17:00 Cours PER 21, Room C230
    25.05.2020 14:15 - 17:00 Cours PER 21, Room C230
  • Assessments methods

    Examen écrit - SP-2020, Session d'été 2020

    Date 18.06.2020 14:00 - 16:00
    Assessments methods By rating
    Descriptions of Exams

    COVID-19 - SS2020 / Exam session SUMMER 2020

    Written Online-Exam

    Duration: 120 minutes

     

     

    Selon modalité A de l'annexe du plan d'études en informatique

    Requirements L'admission à l'examen est soumise à la condition d'avoir passé 10/13 des devoirs au 31.05.2020, selon les critères de validation de l'examen définis dans les informations du cours.
  • Assignment
    Valid for the following curricula:
    Additional Courses in Sciences
    Version: ens_compl_sciences
    Paquet indépendant des branches > Advanced courses in Computer Science (Bachelor level)

    Computer Science 120
    Version: 2019_1/V_01
    BSc in Computer science, Major, 2nd-3rd year > Computer Science 2nd and 3th year (from AS2019 on)

    Computer Science 30
    Version: 2019_1/V_01
    Minor in Computer science 30 > Computer Science, Minor 30 or 60 ECTS elective (from AS2019 on)

    Computer Science 60
    Version: 2019_1/V_01
    Minor in Computer Science 60 > Computer Science, Minor 30 or 60 ECTS elective (from AS2019 on)

    Computer Science 50 [BSc/BA SI]
    Version: 2019_1/V_01
    BSc_SI/BA_SI, Computer science 50 ECTS, 1st-3rd years > BSc_SI/BA_SI, Computer Science, 2nd-3rd years, elective courses for 50 ECTS (from AS2018 on)

    Computer Science [TDHSE] 60
    Version: 2019_1/V_01
    Minor in Computer Science (TDHSE) 60 > Computer Science, Minor TDHSE 60 ECTS elective (from SA2019 on)

    Information Systems 180 ECTS [BA]
    Version: 2014
    3rd year 60 ECTS > 3rd year courses > min. 9 ECTS cours Informatique à choix

    Information Systems 180 ECTS [BA]
    Version: 2018/SA_V01
    3nd year 60 ECTS > 3rd year courses > Cours à choix min. 14 ECTS / Wahlkurse min. 14 ECTS > Apprentissage automatique / Maschinelles Lernen / Machine learning