Course content

The course contains a selection of some of the following topics within artificial intelligence (AI), with application towards intelligent machines and physical/embodied AI:

• introduction to AI and intelligent agents
• search algorithms (e.g., DFS, BFS, UCS, greedy,, A*, minimax, expectimax)
• intelligent optimization algorithms (e.g., evolutionary algorithms, particle swarm optimization, constraint satisfaction problems (CSP) etc.)
• fuzzy expert systems
• artificial neural networks
• reinforcement learning
• advanced control techniques, e.g. model predictive control and Lyapunov stability
• agent-based modelling and simulation
• machine vision
• generative AI and LLMs/VLMs
• possibly other topics

More details about the curriculum will provided during the start of semester.

This course can also be taken by exchange students or other students not enrolled in the study programme, provided they have a suitable background and permission is granted by the course coordinator.

Learning outcome

Knowledge and skills

Upon completion of the course, students can do the following in the context of AI andintelligent machines:

• describe AI in terms of the analysis and design of intelligent agents or systems that interact with their environments
• explain relevant AI terminology, models, and algorithms used for problem-solving, as well as limitations and risks
• model problems in suitable state space depending on choice of solution method
• simulate models and solve real-world problems by means of appropriate choice of AI methods
• use AI methods for cyber-physical systems
• analyse models, methods, simulations, and physical tests and results

Competence

Upon completion of the course, students can

• consult reliable sources on AI and present real-world problems, choice of methods, and results in a short, concise manner
• discuss and communicate advantages and limitations of selected AI methods for problem-solving in a scientific manner
• reflect upon and discuss opportunities and threats of AI in human society, and what measures may be required to make AI beneficiary to human society, including aspects of ethics and sustainability

Learning methods and activities

Learning activities generally include a mix of lectures, seminars, tutorials and practical lab/project work. A constructivist approach for learning is endorsed, with focus on problem solving and practical application of theory.

Compulsory assignments

• Compulsory activities

Specific conditions

Required previous knowledge

he course has no prerequisites. It is a requirement that students are either (a) enrolled in the study programme to which the course belongs, or (b) taking the course as an exchange student. Other exceptions may be made upon approval from the academic director of the study programme.

Course materials

An updated course overview, including curriculum, is presented at the start of the semester.

Credit reductions