Introduction to Machine Learning - GIF-7015

Synopsis: This course focuses on methods for making inferences from observations of classification, regression, data analysis or decision-making models. These methods are characterized by a training phase using data or experiments to perform tasks that would be difficult or impossible to do using more conventional algorithmic means. The course discusses various approaches to learning and seeks to explain their basic mechanisms. An applicative perspective of these different techniques is also presented, with a particular emphasis on the use of modern software tools.

• Course descriptions
• Course page on monPortail
• YouTube channel
• Professor: Christian Gagné

---

Planning and presentations

• Week 1 (videos )
  • Course overview (slides )
  • Machine learning (slides )
  • Supervised learning (slides )
• Week 2 (videos )
  • Bayesian decision theory (slides )
  • Parametric methods (slides )
• Week 3 (videos )
  • Multivariate methods (slides )
  • Scikit-learn (slides )
• Week 4 (videos )
  • Nonparametric methods (slides )
• Week 5 (videos )
  • Linear discriminants (slides )
• Week 6 (videos )
  • Kernel methods (slides )
• Week 7 (videos )
  • Multilayer perceptron (slides )
• Week 8 (videos )
  • Deep learning (slides )
• Week 10 (videos )
  • Deep Networks Architectures (slides )
  • PyTorch (slides )
• Week 11 (videos )
  • Ensemble methods (slides )
• Week 12 (videos )
  • Data preprocessing and analysis (slides )
• Week 13 (videos )
  • Clustering (slides )
• Week 14
  • Models configuration and experiments (slides )

---

Projects

• Best team project posters from Fall 2022
  • Classification de signaux audio basée sur l’activité électrique du cerveau des patients épileptiques
  • Des chats créés par un IA
• Some team projects from Fall 2021 (videos )

---