The course covers the concepts, models and computation methods for computer programs and systems that can autonomously, learn and generalise new knowledge and feature self-awareness.

After the course the student should be able to

• demonstrate knowledge of the disciplinary foundation and of proven experience in the design and analysis of systems built using principles of artificial intelligence

• demonstrate in-depth knowledge of methods and theories in the field of artificial intelligence

• demonstrate abilities to develop learning techniques and systems based on human needs as well as the society’s goals for sustainable development

• demonstrate the ability to identify, formulate, design, and implement learning components and applications

• demonstrate the ability to critically evaluate and compare different AI models and learning algorithms for different problem setups and quality characteristics

• demonstrate the ability to model, predict and evaluate the events even with limited information

Topics covered include: basic methodology, paradigms for artificial intelligence, learning methods and strategies including neural networks, evolutionary methods, instance-based learning, reinforcement learning. Methods for evaluating learning outcomes. Declarative languages, knowledge models, reasoning models. Agent architectures. Fuzzy sets.  Cognitive decision making. Associative memory. Applications including robotics and automation.

The education consists of lectures, laboratory work and a seminar assignment. The laboratories are presented orally and may be provided with a deadline for submission. There are no elective course elements.  Unapproved students must retake the unsuccessful examination moment next time the course is given.