Entry requirements

120 credits including 15 credits in mathematics and 60 credits in computer science/information systems, including 20 credits in programming/algorithms/data structures.

Learning outcomes

After the course, the students shall be able to:

• describe how, and why, natural computation methods work, explain principles and show examples.
• set up and solve typical problems, by implementation or by using established computer simulation tools, decide which machine learning methods/algorithms are suitable for which type of learning problems, i.e. know about their most important weaknesses and advantages,
• recognize typical effects of bad choices (problem setup and parameter selection, for example) and determine how the results can be improved based on this,
• plan an open project so that it can be implemented within the given limits.

Content

The course introduces various natural computation methods. The course is divided into a theoretical part and a practical part.

The theoretical part consists of lectures and literature on various topics, including (but not limited to):

• learning paradigms (supervised, unsupervised and reinforcement learning),
• artificial neural networks for classification, function approximation and clustering,
• deep learning,
• reinforcement learning and temporal difference learning,
• evolutionary computing (genetic algorithms and genetic programming), and
• swarm Intelligence (ant colony optimisation, particle swarm optimisation).

The practical part consists of lab assignments and a self-chosen project task. The subject of the project assignment is defined by the students themselves, but must be approved by the course teacher before the work begins.

Instruction

Lectures, labs and project.

Assessment

Written exam (4 credits), written and oral examination of assignments (6 credits).

Other directives

The course cannot be included in the same degree as 1DT071, 1DT022, or 1DT646