Machine learning : regression, deep networks and dimensionality reduction

lelec2870  2020-2021  Louvain-la-Neuve

Machine learning : regression, deep networks and dimensionality reduction
Due to the COVID-19 crisis, the information below is subject to change, in particular that concerning the teaching mode (presential, distance or in a comodal or hybrid format).
5 credits
30.0 h + 30.0 h
Q1
Teacher(s)
Language
English
Main themes
Linear and nonlinear data analysis methods, in particular for regression and dimensionality reduction, including visualization.
Aims

At the end of this learning unit, the student is able to :

1 With respect to the AA referring system defined for the Master in Electrical Engineering, the course contributes to the develoopment, mastery and assessment of the following skills :
  • AA1.1, AA1.2, AA1.3
  • AA3.1, AA3.2, AA3.3
  • AA4.1, AA4.2, AA4.4
  • AA5.1, AA5.2, AA5.3, AA5.5
  • AA6.3
At the end of the course, students will be able to :
- Understand and apply machine learning techniques for data and signal analysis, in particular for regression and prediction tasks.
- Understand and apply linear and nonlinear data visualization techniques.
- Evaluate the performances of these methods with appropriate techniques.
- Choose between existing methods on the basis of the nature of data and signals to be analyzed.
 
Content
  • Linear regression
  • Nonlinear regression with multi-layer perceptrons (MLP)
  • Deep learning (convolutional CNN and adversarial GAN)
  • Clustering and vector quantization
  • Nonlinear regression with radial-basis function networks (RBFN)
  • Model selection
  • Feature selection
  • Principal Component Analysis (PCA)
  • Nonlinear dimensionality reduction and data visualization
  • Independent Component Analysis (ICA)
  • Kernel methods (SVM)
Teaching methods

Due to the COVID-19 crisis, the information in this section is particularly likely to change.

Ex-cathedra course organized physically if sanitary conditions permit, and broadcasted or recorded if required by sanitary rules.  Practical sessions on computers, and project to be carried out individually or by groups of 2 students.
Evaluation methods

Due to the COVID-19 crisis, the information in this section is particularly likely to change.

Closed book hybrid written-oral exam.  The project is part of the evaluation.  Examination modalities may be adapted according to sanitary conditions and to the number of registered students.
Bibliography
Divers livres de références (mais non obligatoires) mentionnés sur le site du cours
Teaching materials
  • slides disponibles sur Moodle - slides available on Moodle
Faculty or entity
Force majeure
Teaching methods
Ex-cathedra course broadcasted or recorded.  Practical sessions on computers, and project to be carried out individually or by groups of 2 students.
Evaluation methods
Exam organized during the January session, physically in Louvain-la-Neuve unless the sanitary situation does not allow on-site exams anymore: open book written exam.  In the situation of postponed exam or enrollment to another session, the exam may be transformed into an oral exam, depending on the number of registered students.  The project is evaluated, and the written or oral exam may include part of the project.


Programmes / formations proposant cette unité d'enseignement (UE)

Title of the programme
Sigle
Credits
Prerequisites
Aims
Master [120] in Data Science : Statistic

Master [120] in Linguistics

Master [120] in Computer Science and Engineering

Master [120] in Computer Science

Certificat d'université : Statistique et sciences des données (15/30 crédits)

Master [120] in Electrical Engineering

Master [120] in Mathematical Engineering

Master [120] in Agricultural Bioengineering

Master [120] in Forests and Natural Areas Engineering

Master [120] in Environmental Bioengineering

Master [120] in Data Science Engineering

Master [120] in Chemistry and Bioindustries

Master [120] in Data Science: Information Technology

Master [120] in Statistic: General

Master [120] in Biomedical Engineering