The students are expected to have basic knowledge of linear algebra, probability theory and calculus equivalent to MA-223 Statistikk, MA-178 Mathemetics 1 and MA-179 Mathematics 2.

Learning outcomes

Upon completion of the course, the students should

have a general knowledge of mathematics used in machine learning and artificial intelligence

understand how random variables are described

understand how the chain rule is used in machine learning

understand concepts including maximum likelyhood estimation, regression techniques, classification evaluation, and dimensional re-duction techniques

have a general knowledge of Mathematical Game Theory and Markov chains

be able to develop time dependent, deterministic, and stochastic state space functions

Course contents

The course focuses on mathematical principles needed for practical machine learning tasks. This includes:

probability and information theory including random variables, chain rule of the conditional probabilities, and properties of mathematical functions commonly used on machine learning

topics from linear algebra essential for machine learning tasks

numerical computations including gradient descent and constrained optimization

core mathematical concepts in machine learning such as maximum likelyhood estimation, regression techniques, classification evaluation, and dimensional re-duction techniques

identifying and developing solutions for Mathematical Game theory

developing dynamical systems including but not limited to time dependent functions, deterministic and stochastic state space, and evolution rules

the theory and practice of Markov chains

Teaching methods

The course is organized with a combination of lectures, assignments, paper studies, labs, and report writing. The tasks are done individually or in small groups with group supervision. The work load for the average student is approximately 200 hours.

Assessment methods and criteria

Graded portfolio assessment. Information about the content of the portfolio will be given in Canvas at the start of the semester.

Evaluation

The person responsible for the course decides, in cooperation with student representative, the form of student evaluation and whether the course is to have a midway or end of course evaluation in accordance with the quality system for education, chapter 4.1.

Offered as Single Standing Module

Yes, if there are places available.

Admission Requirement if given as Single Standing Module

Admission requirements for the course are the same as for the master’s programme in ICT.

Other information

The course is taught for the first time in the autumn semester 2022.