This course introduces students to the fundamental principles of Machine Learning, with a strong focus on building intuition and practical understanding of core concepts.
The course adopts a hands-on approach that teaches students how to reason about data,  models, and learning behaviour in a structured way.
Students apply machine learning techniques to real-world datasets using commonly used tools and libraries (Scikit-learn, PyTorch). Through practical exercises, assignments, and interactive coding sessions, they learn how to train, evaluate, and interpret machine learning models, as well as understand their limitations.
Some of the topics covered include (non-exhaustive list):

• Introduction to machine learning and data-driven modeling
• Supervised learning (linear regression, logistic regression, decision trees)
• Unsupervised learning (clustering)
• Overfitting vs underfitting
• Neural networks
• Deep learning (CNNs)
• Practical considerations and limitations of machine learning systems