Entry requirements

165 credits including 10 credits in computer programming, 5 credits in scientific computing, 20 credits in mathematics, and 5 credits in statistics and probability theory. Proficiency in English equivalent to the Swedish upper secondary course English 6.

Learning outcomes

On completion of the course the student shall be able to

• apply modern methods for automated machine learning,
• explain and compare modern AI methods, for application in Industrial Analytics.

Content

Methods for automated machine learning like hyperparameter optimization, meta-learning ("learning to learn"), neural network structural search/optimization, and performance estimation. Comparison among alternative AI methods like unsupervised, supervised and interactive machine learning; Bayesian decision theory; optimal design of experiments; adaptive optimal predictive control; multi-agent systems. Studies of industrial application examples from areas like manufacturing; process monitoring and control; business intelligence; asset portfolio management; autonomous vehicles; experimental research & development laboratories; healthcare; cyber security, telecommunication, wireless sensor networks.

Instruction

Lectures, seminars, laboratory sessions and supervision of project.

Assessment

Written examination, and written and oral presentation of project work.

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 targeted pedagogical support from the disability coordinator of the university.