This course explores the mathematical foundations of Machine Learning, bridging theoretical Linear Algebra and Continuous Optimization with modern algorithmic design. Rather than treating mathematics as an isolated abstract exercise, concepts are introduced strictly in tandem with their practical utility in machine learning models, scaling from classical closed-form estimators to state-of-the-art neural network optimizers.

This course explores the foundations of Supervised Machine Learning through a rigorous probabilistic and statistical lens. Students will learn how to predict labels and continuous targets from observed data, treating each algorithm not as a black box but as an estimator with explicit distributional assumptions, an associated likelihood, and quantifiable error behavior.

This course explores the foundations of Unsupervised Machine Learning and Representation Learning through a rigorous probabilistic and statistical lens. Students will learn how to extract patterns, model underlying distributions, and discover hidden structures in unlabeled data using advanced statistical frameworks and information theory.