Duration
25h Th, 45h Proj.
Number of credits
Lecturer
Language(s) of instruction
English language
Organisation and examination
Teaching in the second semester
Schedule
Units courses prerequisite and corequisite
Prerequisite or corequisite units are presented within each program
Learning unit contents
The goal of this course is to prepare students to the study of state-of-the-art research in the field of machine learning.
The class will be organized as a journal club, with reading and presentation assignments of recent machine learning research papers.
In terms of content, this course will focus on advanced topics in machine learning, including supervised learning, unsupervised learning and non-standard learning protocols such as semi-supervised learning, transfer learning or active learning. It will cover different families of techniques, such as neural networks, graphical models or kernel-based methods.
From the practical viewpoint, the emphasis will be on machine learning problems dealing with high-dimensional and structured representation spaces (e.g. texts, images, videos, time-series, and graphs).
Learning outcomes of the learning unit
At the end of the class, the students are expected to master the state of the art in the field of machine learning. They will be able to implement, combine, or extend existing algorithms to address very complex machine learning tasks, and they will have the theoretical background to read scientific papers and start doing research in the field.
Prerequisite knowledge and skills
The course relies strongly on linear algebra, probability calculus, elementary statistics, and notions of optimization, as well as good knowledge of data structures and algorithms.
A prior introduction to machine learning, information theory, and graphical models, is highly recommended.
A strong interest in advanced applications of machine learning is expected from the students, as well as willingness to self-learn in an autonomous way and to present their ideas in a clear fashion during the course lectures.
Planned learning activities and teaching methods
This course, preparing to research, needs an active participation of the student. Ex-cathedra lectures given by the professors will be supplemented by discussion sessions with the students around key papers in the field, and by research seminars given by external speakers.
Personal student projects will consist in the critical reading, discussion and oral presentation of a selection of scientific papers on the topics related to the course.
Mode of delivery (face to face, distance learning, hybrid learning)
face-to-face
Organisational adjustments related to the current health context
Recommended or required readings
See course web-page: https://github.com/glouppe/info8004-advanced-machine-learning
Assessment methods and criteria
Below you will find information on the evaluation methods planned for in-person and remote exams as well as those planned for hybrid sessions. Depending on how the health crisis evolves, the chosen method will be communicated to you no later than one month before the start of the exam session.
The students will carry out a mandatory reading and presentation assignment by groups of 3 students. It will consist in reading recent research papers and presenting them during a lecture to the rest of the students.
The oral exam will consist in the presentation and in the critical summary of a self-selected scientific paper. The presentation will be complemented by a written summary, in the format of a scientific technical report.
Weighting:
- Exam: 60%
- Reading and presentation assignment: 40%
Work placement(s)
None
Organizational remarks
This course is organized in full-English mode.
Contacts
Teachers: Profs. Pierre Geurts (p.geurts@uliege.be), Gilles Louppe (g.louppe@uliege.be) and Louis Wehenkel (l.wehenkel@uliege.be)