IFT 3710/6759 H22 - Projets (avancés) en apprentissage automatique
The objective of this course is to prepare you, the students, for tackling real-world machine learning projects. During the course, you will work on the main stages of machine learning projects, including data acquisition, data pre-processing, model training, analysis of results and presentation of results and conclsions. Skills developed during this course include literature review of a particular problem, practical and theoretical machine learning, Python for data science, PyTorch, version control with
git and basic Linux commands.
- Introduction to the course
- Version control with
- Linux and Python for machine learning
- HPC clusters
- Machine learning review
- Deep learning review
- Data visualisation
- Advanced PyTorch tutorial
- Projects work
Students will be evaluated entirely according to their work on projects. Depending on the complexity of the projects, you will be required to take part in one or two projects and work in teams of 3–5 people. You can choose from a list of projects prepared by the instructors, or propose your own projects, provided they meet certain criteria. The final evaluation will take the following into account:
- Difficulty of the project
- Performance of the developed algorithms
- Oral presentation
- Written report
- Quality of the code
- The evaluation criteria will be slightly relaxed for undergraduate students (IFT 3710).
- The grade will be binary (pass or fail), not in a letter scale.
- The teams should not mix graduate (IFT 6759) and undergraduate students (IFT 3710).
All students will be required to pass a basic skills test and interview before starting the project work, in order to ensure that they are ready to work on an advanced machine learning project in a team.
- Projects guidelines
- Instructions for the presentation, final report and code
- Link to StudiUM page
- Link to public admission page of IFT 6759
- Link to public admission page of IFT 3710
Winter term 2022
Classes take place on:
- Wednesdays, 16:30–18:30 (ET): 1140 Pav. André-Aisenstadt
- Fridays, 09:30–11:30 (ET): Y-117 Pav. Roger-Gaudry
Due the pandemic situation, la Faculté des arts et des sciences of the Université de Montréal has delayed the start of the term until January 10th. Therefore, the first session of this course will be on Wednesday January 12th. For the same reasons, classes will be online at least until January 31st.
Starting on January 31st, classes take place in person.
- Abu-Mostafa, Y. S., Magdon-Ismail, M., & Lin, H. T. (2012). Learning from data. AMLBook.
- Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press.
- Anish, Jose, Jon (last seen on Dec. 2021). The Missing Semester of Your CS Education. CSAIL MIT.