Statistical Information Theory

Information theory is at the intersection of mathematics, statistics, computer science and several other fields, with applications in many areas.

The course treats information theory with applications to statistics, machine learning, time series analysis, dynamical systems and physics. In particular, rates of entropy of stochastic processes, differential entropy, flow of information and causal detection, multivariate dependencies and multi-information, is treated.

This course replaces the earlier version with course code MT7037.

The course consists of two modules, theory and hand-in assignments.

Teaching Format

Instruction is given in the form of lectures, exercise sessions and supervision.

Assessment

Assessment takes place through a written exam, and hand-in assignments.

Examiner

The schedule will be available no later than one month before the start of the course. We do not recommend print-outs as changes can occur. At the start of the course, your department will advise where you can find your schedule during the course.
Note that the course literature can be changed up to two months before the start of the course.
Course reports are displayed for the three most recent course instances.

Cookie settings

By allowing third-party services, you accept their cookies and the use of tracking technologies necessary for them to function properly.