Machine learning is at the heart of modern data science, powering applications from medical diagnostics to language technology. This course provides a rigorous introduction to the mathematical and statistical foundations of machine learning, focusing on the theory behind widely used algorithms and how they are applied in practice.
You will learn to:
-
Formulate supervised and unsupervised learning problems.
-
Understand the principles of Bayesian decision theory.
-
Apply parametric and non-parametric methods to real datasets.
-
Reduce high-dimensional data with techniques such as PCA.
-
Cluster data and evaluate clustering solutions.
-
Analyse model complexity, overfitting, and generalisation.
The course combines theory and practice: weekly video lectures and quizzes build your conceptual understanding, while short Python programming assignments give you hands-on experience with implementing algorithms and evaluating them on real data.
This is the first part of a three-course sequence on the Foundations of Machine Learning. Later courses cover advanced models such as kernel machines, ensembles, deep learning, reinforcement learning, and modern generative and transformer-based approaches.
Who is this course for?
The course is intended for students of mathematics, applied mathematics, statistics, and computer science, but is open to anyone with a solid mathematical background. Prior knowledge of probability, statistics, linear algebra, and algorithms is helpful but not strictly required. Motivation and readiness to work with mathematical concepts and Python coding are more important.
By the end of the course, you will have the foundations needed to understand how machine learning works, evaluate its results critically, and apply core methods to real-world data.
- Teacher
Ion Petre