Ense3_bandeau_rubrique_formation

Machine Learning and Optimization - 5EU9MLO0

  • Number of hours

    • Lectures -
    • Projects -
    • Tutorials -
    • Internship -
    • Laboratory works 50.0
    • Written tests -

    ECTS

    ECTS 5.0

Goal(s)

The objective of the course is to provide a comprehensive understanding of the theory and practice of machine learning, primarily in the area of smart energy systems.

At the end of the module, students will be able to:

  • Understand the fundamentals of machine learning algorithms (error-based, similarity-based, probability-based and information-based learning algorithms.)
  • Select and implement machine learning methods appropriate to the applications under consideration.
  • Work with real-world data sets (analyze, understand, predict, prescribe) using data science and artificial intelligence tools.

Responsible(s)

Vincent DEBUSSCHERE

Content(s)

Lab part

1) Introduction to machine learning
2) Supervised learning (classification, regression)
3) Unsupervised Learning (Clustering)
4) Data Analysis (Pandas-Python)
5) Project: Estimation occupancy & Load forecasting

Practical work part

1) Discovery of database and visualization of data (InfluxDB, Grafana)
2) Analysis of data provided by a real home automation (ExpeSmartHouse)

Prerequisites

  • Experience in Python programming (Numpy, Pandas and Matplotlib)

Test

  • Specific credits: this course brings 3.0 ECTS to students in Year 2 Master Sciences in Electrical Engineering for Smart Grids and Buildings (M2 SGB)
  • Session normale / First session
    Evaluation rattrapable (ER) / ER assessment: Projet ML
    Evaluation non rattrapable (EN) / EN assessment : Exercices et Comptes-rendus de laboratoire (ML et Optimisation) / exercices and lab reports

Si situation 100% distancielle / If remote situation:
Evaluation rattrapable (ER) / ER assessment: Projets
Evaluation non rattrapable (EN) / EN assessment : Exercices et Comptes-rendus de laboratoire / exercices and lab reports
---------------
Session de rattrapage / Second session
Evaluation non rattrapable (EN) / EN assessment

Moyenne de l'UE = EN 100%

The exam is given in english only FR

Calendar

The course exists in the following branches:

see the course schedule for 2024-2025

Additional Information

Course ID : 5EU9MLO0
Course language(s): FR

You can find this course among all other courses.

Bibliography

Warwick, Kevin, Arthur Ekwue, and Raj Aggarwal, eds. Artificial intelligence techniques in power systems. No. 22. Iet, 1997.

French State controlled diploma conferring a Master's degree

diplôme conférant grade de master contrôlé par l'Etat