This course is an introduction to the basic concepts of machine learning, including supervised and unsupervised learning with neural networks, reinforcement learning, and methods to make the learned results interpretable. The material is presented with scientific research applications in mind, where data has often very peculiar structure and quantitative accuracy is paramount.
Learning objective
The goal is to become familiar with basic machine learning techniques for scientific applications, through lectures and practical programming exercises.
Content
Machine learning algorithms enjoy a large and increasing number of technological applications. They help us to extract relevant information from big datasets and transform the way we interact with machines. In the sciences, machine learning emerges as a more and more routinely used tool with applications in physics, geography, medicine, chemistry, biology and more. This course offers an introduction to the basic concepts, including supervised and unsupervised learning with neural networks, reinforcement learning, and methods to make the learned results interpretable. The material will be presented with scientific research applications in mind, where data has often very peculiar structure and quantitative accuracy is paramount. In the exercise class, examples will be implemented with openly available machine learning libraries.
The lecture an exercise class will be held at Y24-G-55 (Uni Zürich, Irchel Campus) and streamed as well as recorded. The recording of the lecture will be made available afterwards, but it is highly recommended to join the lecture or the live stream. Several seats outside of the field of view of the camera are available.
Performance assessment as a semester course