Advanced Topics in Data Analytics and Machine Learning

  • Teaching

    Details

    Faculty Faculty of Management, Economics and Social Sciences
    Domain Economics
    Code UE-EEP.00517
    Languages English
    Type of lesson Seminar
    Level Master
    Semester SA-2023

    Schedules and rooms

    Summary schedule Wednesday , Cours bloc (Autumn semester)
    Hours per week 1

    Teaching

    Responsibles
    • Huber Martin
    Teachers
    • Huber Martin
    Description

    Deep Learning with Python - from tabular to multimedia (taught by Dr. Christian Kauth)

    Deep learning with neuralnetworks is a fascinating field, especially on non-tabular data (like images and text). The mixture of faster hardware, new techniques, highly optimized open source libraries and large datasets allow very large networks to be created with frightening ease. Deep neural networks have repeatedly proven impressively skillful on a range of problems.

    This course is a guide to deep learning in Python. You will discover the Keras Python library for deep learningandhowtouseittodevelopandevaluatedeeplearningmodels.Youwilldiscoverthetechniques and develop the skills in deep learning that you can then bring to your own machine learning projects.

    After familiarizing with Keras, we will illustrate the skill of deep learning on some well-understood case study machine learning problems from the UCI Machine learning repository (http://archive.ics.uci.edu/ml/index.php)andcomparetheperformancetotheclassicalmachinelearning approaches used in the course “Machine Learning with Python – from Zero to Hero”. Next we introduce convolutional layers to the networks and use them to classify handwritten digits (e.g. MNIST dataset http://yann.lecun.com/exdb/mnist/) and real-world objects (e.g. CIFAR-10https://www.cs.toronto.edu/~kriz/cifar.html).

    We then shift our focus from images to text data, and learn how to solve common Natural Language Processing (NLP) tasks such as text classification, token classification, summarization and translation. To that purpose, we’ll use state-of-the-art transformer-based pre-trained models and see how to fine-tune them on our own dataset (transfer-learning).

    Lastly you’ll learn how to integratethe temporal dimension into your machine learning projects to make forecasts on time-series. We’ll compare the performance of several techniques, reaching from tabular representation to state-of-the-art causal transformer architectures.

    Fun fact: Deep learning is taking AI performance in compute vision, natural language and time series analysis from deceptive to disruptive, and the Attention mechanism plays a crucial role in this success story. If you’re curious, have a look at the paper “Attention is all you need” https://arxiv.org/abs/1706.0376

    Training objectives
    • To understand the structure and working principles of neural networks and transformers
    • To gain insights into some layer types of feed-forward neural networks (dense, convolutional, dropout, attention, embedding) and how they are trained.
    • To learn how to classify images with neural networks
    • To learn how to solve common NLP tasks with transformers
    • To learn how to frametime-series tasks for machine and deep learning
    • To gain hands-on experience with Python and the deep learning library Keras
    • To be able to leverage and fine-tune state-of-the-art models (from Microsoft, Open AI, Google, Deep Mind, Hugging Face)

     

    Condition of access
    • Fluency in the programming language "Python", as e.g. provider in the course "machine Learning with Python - from Zero to Hero"
    • Google account to access Google Colab

     

     

    Softskills No
    Off field No
    BeNeFri No
    Mobility No
    UniPop No
  • Dates and rooms
    Date Hour Type of lesson Place
    14.02.2024 08:15 - 17:00 Cours PER 21, Room E040
    15.02.2024 08:15 - 17:00 Cours PER 21, Room E040
    16.02.2024 08:15 - 17:00 Cours PER 21, Room E040
  • Assessments methods

    Evaluation continue - SA-2023, Session d'hiver 2024

    Assessments methods By rating
    Descriptions of Exams

    Take home exam: project work to be solved in Python on image, text and time-series data

    Course with continuous evaluation: after the registration period, you can no longer cancel your registration (see session calendar on the Faculty's website).

    No retake exam

  • Assignment
    Valid for the following curricula:
    Ma - Accounting and Finance - 120 ECTS
    Version: 2024/SP_V01_DD_Caen
    UniFr courses > Elective courses - Max 18 ECTS > SES Master level courses

    Ma - Accounting and Finance - 90 ECTS
    Version: 2021/SA_V01 Dès SA-2024
    Course - 72 ECTS > Minimum 0 / maximum 1 optional master course offered at the University of Fribourg, if 72 ECTS not yet reached in the above modules > SES Master level courses

    Ma - Business Communication : Business Informatics - 90 ECTS
    Version: 2020/SA_V02
    Courses - 60 ECTS > Option Group > Information Management > Cours > Module Informatik > Data Science

    Ma - Business Informatics - 90 ECTS
    Version: 2020/SA-v01
    Classes - min. 45 ECTS > Module IT and IT Management > Data Science

    Ma - Communication and Media Research - 90 ECTS
    Version: 2015/SA_V01
    Courses - 60 ECTS > Inter- and Transdisciplinary Perspectives > SES Master level courses

    Ma - Communication and Society - 90 ECTS
    Version: 2021/SA_V03
    Forschungsbereiche > Inter- & Transdisciplinary Perspectives

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

    Ma - Economics - 90 ECTS
    Version: 2021/SA_V04
    Le choix de l'option se fait par l'inscription au premier cours dans l'une des options possibles. > Sustainable Development and Social Responsibility > Elective courses in Sustainable Development and Social Responsibility > Elective courses in Economics
    Le choix de l'option se fait par l'inscription au premier cours dans l'une des options possibles. > Sustainable Development and Social Responsibility > Elective courses in Sustainable Development and Social Responsibility > Elective courses of the SES Faculty - max. 15 ECTS > SES Master level courses
    Le choix de l'option se fait par l'inscription au premier cours dans l'une des options possibles. > Public Economics and Policy > Elective courses in Public Economics and Policy > Elective courses in Economics
    Le choix de l'option se fait par l'inscription au premier cours dans l'une des options possibles. > Public Economics and Policy > Elective courses in Public Economics and Policy > Elective courses of the SES Faculty - max. 15 ECTS > SES Master level courses
    Le choix de l'option se fait par l'inscription au premier cours dans l'une des options possibles. > Business Economics > Elective courses in Business Economics > Elective courses in Economics
    Le choix de l'option se fait par l'inscription au premier cours dans l'une des options possibles. > Business Economics > Elective courses in Business Economics > Wahlkurse der SES-Fakultät - max. 15 ECTS > SES Master level courses
    Le choix de l'option se fait par l'inscription au premier cours dans l'une des options possibles. > Quantitative Economics > Elective courses in Quantitative Economics
    Le choix de l'option se fait par l'inscription au premier cours dans l'une des options possibles. > Quantitative Economics > Elective courses in Quantitative Economics > Courses from the SES faculty - max. 15 ECTS > SES Master level courses
    Course selection for the Master WITHOUT options > Elective courses > Elective courses in Economics
    Course selection for the Master WITHOUT options > Elective courses > Elective courses of the SES Faculty - max. 15 ECTS > SES Master level courses

    Ma - European Business - 90 ECTS
    Version: 2017/SA_v01
    Courses - 63 ECTS > Additional courses: Any Master courses of the Faculty of Economics and Social Sciences, as well as maximum 9 ECTS from all Master programmes of the University. > SES Master level courses

    Ma - International and European Business - 90 ECTS
    Version: 2021/SA_v01 dès SA-2024
    Courses > Additional courses > SES Master level courses

    Ma - Management - 90 ECTS
    Version: 2021/SA_v03 dès SA-2024
    Courses: min. 72 ECTS > Elective courses > SES Master level courses

    Ma - Management - 90 ECTS [MA]
    Version: 2017/SA_v01
    Courses: min. 63 ECTS > Cours facultatifs : max. 18 ECTS > SES Master level courses

    Ma - Marketing - 90 ECTS
    Version: 2021/V03 dès SA-2024
    Courses - 72 ECTS > Elective Master courses from the whole university > SES Master level courses

    Ma - Public Economics and Public Finance - 90 ECTS
    Version: 2021/SA_V01_DD_PEPF
    Cours > Up to 40 ECTS credits must fulfill the conditions required for the specialisation according to the approuved document "Individual choice of lectures". > Elective courses in Economics

    MiMa - Business Informatics - 30 ECTS
    Version: 2020/SA_V01
    Cours > Module Informatik > Data Science

    MiMa - Data Analytics - 30 ECTS
    Version: 2020/SA-v01
    À choix 9 crédits ECTS > Data Science

    MiMa - Economics - 30 ECTS
    Version: 2021/SA_V01
    Elective courses > Elective courses in Economics