Entry requirements

120 credits including Probability and Statistics, Linear Algebra II, Single Variable Calculus, Statistical Machine Learning, a course in several variable analysis and a course in introductory programming.

Learning outcomes

On completion of the course the student shall be able to:

• discuss and determine if an engineering-related problem can be formulated as a supervised or unsupervised machine learning problem, and to make this formulation.
• account for similarities and differences (both practical and theoretical) between probabilistic and "traditional" machine learning methods.
• demonstrate familiarity with and argue for a probabilistic approach, and be able to interpret and explain the outcome from probabilistic machine learning methods.
• derive, analyse and implement the probabilistic methods which are included in the course.
• analyse, implement and use methods for nonlinear dimensionality reduction.

Content

This is an advanced course in machine learning, focusing on modern probabilistic/Bayesian methods: Bayesian linear regression, Bayesian networks, latent variable models and Gaussian processes, as well as methods for exact and approximate inference in such models. The course also contains necessary probability theory and methods for data dimensionality reduction.

Instruction

Lectures, problem solving sessions (both with and without computer), laboratory work, feedback on written assignments.

Assessment

Oral exam combined with oral and written presentation of assignments.

If there are special reasons for doing so, an examiner may make an exception from the method of assessment indicated and allow a student to be assessed by another method. An example of special reasons might be a certificate regarding special pedagogical support from the disability coordinator of the university.