Duration
Theory : 24h Th
Practical work : 6h Pr, 10h AUTR
Number of credits
Lecturer
Theory : Vân Anh Huynh-Thu
Practical work : Vân Anh Huynh-Thu
Coordinator
Language(s) of instruction
French language
Organisation and examination
Teaching in the first semester, review in January
Schedule
Units courses prerequisite and corequisite
Prerequisite or corequisite units are presented within each program
Learning unit contents
Theory
This course focuses on machine learning, a subfield of artificial intelligence (AI) that involves training a computer to perform a specific task based on data related to that task. The applications of machine learning are now ubiquitous, ranging from film and music recommendations to machine translation, bank fraud detection, medical image analysis and the prediction of biological phenomena.
This course aims to introduce you to the fundamental principles of the main machine learning algorithms, as well as methods for manipulating, analysing and visualising data.
The topics covered will be as follows (subject to change):
- Exploratory data analysis (graphical and non-graphical analysis)
- Standard machine learning (nearest neighbour algorithm, linear models, tree-based methods, performance estimation)
- Deep learning (artificial neural networks, generative AI)
- Interpretability in AI and explainable AI
- Unsupervised learning (clustering, dimensionality reduction)
Practical work
The second part of the course aims to put the concepts covered in the first part into practice, through pratical tutorial sessions and a project, both to be completed on a computer.
Learning outcomes of the learning unit
Theory
At the end of the course, you will have acquired an overview of the main machine learning algorithms.
Practical work
At the end of the second part of the course, you will be able to apply the main machine learning algorithms to real data and rigorously evaluate their performance.
Prerequisite knowledge and skills
Theory
There is no prerequisite.
Practical work
This part of the course requires basic Python programming knowledge (as covered, for example, in the INFO3001-1 course).
Planned learning activities and teaching methods
Theory
The course consists of theoretical lessons presenting the fundamental principles of machine learning.
Practical work
The pratical exercices will be carried out during sessions supervised by a teaching assistant.
The project is to be carried out remotely. However, (non mandatory) sessions will be held to allow you to work on the project in the presence of the teaching assistant.
Mode of delivery (face to face, distance learning, hybrid learning)
Theory
Face-to-face course
Further information:
The course is given during the first semester.
Practical work
Face-to-face course
Further information:
The course is given during the first semester.
Course materials and recommended or required readings
Theory
Platform(s) used for course materials:
- eCampus
Practical work
Platform(s) used for course materials:
- eCampus
Theory
Exam(s) in session
Any session
- In-person
oral exam
Further information:
The purpose of the oral examination will be to assess your understanding of the concepts covered in the lectures. You will be required to present one or several parts of the course and answer questions covering the entire course material.
Practical work
Exam(s) in session
Any session
- In-person
oral exam
Written work / report
Further information:
The project will be assessed on the basis of a written report and the code. During the oral exam, you will also be required to answer questions about the project you completed. Your answers will be taken into account in the evaluation of the project.
Work placement(s)
Organisational remarks and main changes to the course
Theory
All course information will be posted on eCampus.
Practical work
All course information will be posted on eCampus.
Contacts
Theory
Professor : Vân Anh Huynh-Thu.
Email : vahuynh@uliege.be
Office : 1.84b, B28 (Montefiore Institute, Sart-Tilman)
Practical work
Professor : Vân Anh Huynh-Thu.
Email : vahuynh@uliege.be
Office : 1.84b, B28 (Montefiore Institute, Sart-Tilman)