What's this course about?

This course provides an in-depth exploration of widely used and state-of-the-art machine learning techniques. Building on foundational concepts, we examine advanced methods in both supervised and unsupervised learning, with a strong emphasis on modern developments in the field. Key topics include recent deep neural network architectures—such as Graph Neural Networks and Transformers—Bayesian inference, and deep generative modeling approaches, including Diffusion Models and Flow Matching. The course combines theoretical rigor with practical relevance, highlighting how contemporary methods are applied to real-world challenges. In the accompanying exercise sessions, students will translate theoretical insights into hands-on experience. You will work with modern machine learning tools and frameworks to develop solutions to practical engineering problems. For a more detailed description, see the module handbook.