Foundations of Machine Learning (MILA)

I completed this undergraduate Machine Learning course as part of my Computer Science degree at Université de Montréal, combining theoretical foundations with hands-on implementation and competitive problem solving. The course covered core machine learning concepts including k-nearest neighbors, probabilistic modeling and maximum likelihood, Bayesian and linear classifiers, optimization, kernel methods, neural networks and backpropagation, convolutional neural networks, decision trees, ensemble methods such as bagging and boosting, graphical models, and latent-variable models.

Through practical labs, I implemented and experimented with machine learning methods using tools such as NumPy, scikit-learn, and PyTorch. The course also included two Kaggle competitions, providing an opportunity to apply modeling, experimentation, and performance evaluation in a competitive setting.

The course strengthened my understanding of both the mathematical foundations behind machine learning algorithms and their practical implementation, giving me a stronger foundation for building and evaluating ML-powered systems.

Taught by Prof. Ioannis Mitliagkas, Canada CIFAR AI Chair and Research Scientist at Google DeepMind.