Aller à : contenu haut bas recherche
EN     FR
Vous êtes ici:   UNIL > HEC Inst. > HEC App. > SYLLABUS

Deep Learning

  • Enseignant(s):  
  • Titre en français: Apprentissage approfondi
  • Cours donné en: anglais
  • Crédits ECTS:
  • Horaire: Semestre de printemps 2020-2021, 2.0h. de cours (moyenne hebdomadaire)
      WARNING :   this is an old version of the syllabus, old versions contain   OBSOLETE   data.
  •  séances
  • site web du cours site web du cours
  • Formations concernées:
  • Permalink:




By the end of this course, students must be able to:

  • setup a local/remote workstation for working with artificial neural networks (ANN) using R, {keras} package, and backend library TensorFlow
  • use R package {keras} to manipulate ANN models: build, train, tune hyperparameters, save, and use pretrained neural networks
  • use auxiliary R packages {tfruns} and {cloudml}
  • use Google Cloud AI Platform and Google Colaboratory to train models remotely
  • apply ANN in the context of image recognition and text mining to the cases covered during the course
  • discuss, evaluate, and visualize results provided by ANN models


  • Foundations of ANN: linear regression, perceptron, gradient descent, and backpropagation
  • {keras} and TensorFlow: implementation and manipulation of ANN models
  • Training deep learning networks: hyperparameters tuning, optimization algorithms, activation functions
  • ANN with dense layers and its applications
  • Convolutional Neural Networks and their applications in image recognition and computer vision
  • Recurrent Neural Networks and their applications in text mining and time series
  • Generative adversarial network and autoencoders


  • Chollet, F. and Allaire, J.J. (2018). Deep Learning with R. Manning Publications Co.
  • Géron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, Second Edition. O'Reilly Media, Inc.


  • Students of Master in Management (Business Analytics orientation):

    • Data Science in Business Analytics
    • Machine Learning in Business Analytics (first 7 weeks)
  • PhD and external students:

    • foundations of supervised machine learning (e.g., data splitting strategies, metrics, scoring, etc.)
    • basic calculus knowledge (e.g., derivatives, gradient, etc.)
    • essential skills in R and git/GitHub


1ère tentative

Sans examen (cf. modalités)  

The assessment is based on two parts, namely homework (50%) and a course project (50%). The maximum number of points that can be obtained in this course is 60 points. Each of the five homework is worth 6 points, while the remaining 30 points are allocated to the course project. Students will be asked to submit a project proposal, develop a model(s), communicate results in a report, and present the course project.

During the course students can obtain bonus points (up to 6) by winning competitions or showing a strong performance in quizzes.

The total number of points is then rescaled to the final grade using the table below:

6.0 | 57-60

5.5 | 52-56

5.0 | 47-51

4.5 | 42-46

4.0 | 37-41

3.5 | 32-36

3.0 | 27-31

2.5 | 22-26

2.0 | 17-21

1.5 | 12-16

1.0 | 0-11


Sans examen (cf. modalités)  

A second attempt is solely based on the project (60 points, the same rescaling system is used as in the first attempt). Students should implement proposed modifications to the project and present the project again.

[» page précédente]           [» liste des cours]

Internef - CH-1015 Lausanne - Suisse  -   Tél. +41 21 692 33 00  -   Fax +41 21 692 33 05
Swiss University