Examination arrangement

Course content

The course contains a selection of some of the following topics, with application towards intelligent machines:

• introduction to AI and intelligent agents
• modelling problems terms of performance measure, environment, sensors, and actuators (PEAS)
• analysis and classification of models and algorithms
• uninformed search (e.g., DFS, BFS, UCS, IDS)
• informed (heuristic) search (e.g., greedy BFS, A*)
• adversarial search (e.g., minimax, expectimax, expectiminimax, alpha-beta pruning)
• simulation of models for problem-solving
• optimization problems and intelligent optimization algorithms (e.g., evolutionary algorithms)
• constraint satisfaction problems (CSP)
• artificial neural networks
• reinforcement learning
• fuzzy expert systems
• agent-based modelling and simulation
• hybrid intelligent systems
• possibly other topics

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

Learning outcome

Knowledge and skills

Upon completion of the course, students can do the following in the context of intelligent 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 in the implementation of cyber-physical systems
• analyse models, AI methods, and simulation and test results

Competence

Upon completion of the course, students can

• consult reliable sources on AI and reformulate the presented 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 not only about what AI can do but also what AI should be allowed to do, and what measures may be required to make AI beneficiary to human society

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

Further on evaluation

The final grade is based on an overall evaluation of the portfolio, which consists of work that is carried out, documented and digitally submitted during the term. Such submissions may include some of the following:

• software
• technical reports
• essays
• reflection notes
• video submissions, e.g. demonstration of work or tests of knowledge
• possibly other kinds of submissions.

Both individual and team assignments may be given. Assignments are designed to help students achieve specific course learning outcomes, and formative feedback is given during the period of the portfolio.

The re-sit exam is an oral exam in August.

Note that the course also has some compulsory activities that must be approved in order for the portfolio to be assessed.

More information will be provided at the start of the course.

Specific conditions

Required previous knowledge

The course has no prerequisites. It is a requirement that students are enrolled in the study programme to which the course belongs.

Course materials

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

Credit reductions