Statistical learning and neural networks

  • Teaching

    Details

    Faculty Faculty of Science and Medicine
    Domain Mathematics
    Code UE-SMA.04413
    Languages French , English
    Type of lesson Lecture
    Level Master
    Semester SA-2021

    Schedules and rooms

    Summary schedule Monday 13:15 - 15:00, Hebdomadaire (Autumn semester)

    Teaching

    Responsibles
    • Mazza Christian
    Teachers
    • Mazza Christian
    Description

    This course aims at presenting and studying mathematically models from statistical learning theory, by focusing on deep learning algorithms in multi-layer neural networks. Applications to artificial intelligence will be provided. We will also present and study the basic probabilistic and statistical models of machine learning by making links with neural nets. A special emphasis will be given to deep learning processes for Boltzmann machines using methods from probability theory, statistics and statistical mechanics. 

    Training objectives

    Topics focus on but are not limited to:
    Biological neural networks, mathematical models of neural nets, learning algorithms (Hebb rule) for Hop eld neural nets and Boltzmann machines, machine learning and multivariate statistics (discriminant analysis, regression, support vector machines), general statistical learning theory (deterministic and stochastic models, Vapnik-Cervonenkis theory), learning processes
    in associative memories, perceptron and multi-layer neural nets, stochastic processes for deep learning in Boltzmann machines, thermodynamic extension (statistical mechanics of learning processes), self-organisation, chemical reaction networks and machine learning. If time permits we will also consider recent methods from topology and geometry like manifold learning and
    topological data analysis.

    Comments

    compte pour Mathématiques appliquées

    Softskills No
    Off field No
    BeNeFri Yes
    Mobility Yes
    UniPop No
  • Dates and rooms
    Date Hour Type of lesson Place
    20.09.2021 13:15 - 15:00 Cours PER 07, Room 1.309
    27.09.2021 13:15 - 15:00 Cours PER 07, Room 1.309
    04.10.2021 13:15 - 15:00 Cours PER 07, Room 1.309
    11.10.2021 13:15 - 15:00 Cours PER 02, Room 0.403
    18.10.2021 13:15 - 15:00 Cours PER 02, Room 0.403
    25.10.2021 13:15 - 15:00 Cours PER 02, Room 0.403
    08.11.2021 13:15 - 15:00 Cours PER 02, Room 0.403
    22.11.2021 13:15 - 15:00 Cours PER 02, Room 0.403
    29.11.2021 13:15 - 15:00 Cours PER 02, Room 0.403
    06.12.2021 13:15 - 15:00 Cours PER 02, Room 0.403
    13.12.2021 13:15 - 15:00 Cours PER 02, Room 0.403
    20.12.2021 13:15 - 15:00 Cours PER 02, Room 0.403
  • Assessments methods

    Oral exam - SA-2021, Session d'hiver 2022

    Assessments methods By rating
  • Assignment
    Valid for the following curricula:
    Additional Courses in Sciences
    Version: ens_compl_sciences
    Paquet indépendant des branches > Specialized courses in Mathematics (Master level)

    Additional programme requirements for PhD studies [PRE-DOC]
    Version: 2020_1/v_01
    Additional programme requirements for PhD studies (Faculty of Science and Medicine) > Specialized courses in Mathematics (Master level)

    MSc in Mathematics [MA] 90
    Version: 2022_1/V_01
    MSc in Mathematics, lectures and seminars (from AS2020 on) > MSc-MA, lectures (from AS2018 on)

    Mathematics [3e cycle]
    Version: 2015_1/V_01
    Continuing education > Specialized courses in Mathematics (Master level)

    Mathematics [POST-DOC]
    Version: 2015_1/V_01
    Continuing education > Specialized courses in Mathematics (Master level)