Fundamentals of Artificial Intelligence, 7.5 Credits

Contents

Part 1, theory, 5.5 credits.
The course provides a basic introduction to classical AI (artificial intelligence) as well as non-classical AI. It addresses fundamental conditions, problems and challenges for AI also from a philosophical perspective. Topics covered: Background and history of AI in outline. Fundamental problems and challenges - realism, brittleness, scalability, real-time requirements, the frame problem, the homunculus problem, the substrate problem, symbol grounding, common-sense knowledge and common-sense reasoning. Fundamentals of search: problem, solution, state space, breadth-first, depth-first, heuristics, A*, local search and optimization. Knowledge representation: logic as form of expression (syntax and semantics of propositional logic and predicate logic). Agent paradigms: the hierarchical paradigm, the reactive paradigm, and the hybrid paradigm. Classical planning and execution, STRIPS, Shakey. Reactive agents, Braitenberg vehicles, subsumption architecture. Potential fields architecture. The physical structure of robots. Teleoperation and semi-autonomous robots. Embodied cognition and situatedness. Neural networks: background and fundamentals. Artificial evolution, genetic algorithms - short introduction. Multiple autonomous agents, swarm intelligence, stigmergy, emergence. Learning - short introduction.

Part 2, laboratory, 2 credits.
In the laboratory part some of the theories, methods and principles treated in the theory part are illustrated and practically applied. This part consists of a number of mandatory laboratory assignments, in part carried out with physical robots or advanced simulators.

Expected learning outcomes

After having completed the course the student will be able to:
- give an overview of the field of artificial intelligence, its background, history, fundamental issues, challenges and main directions
- interpret and formulate knowledge representations in the form of logic expressions
- explain basic concepts, methods and theories for search
- account for classical planning of proactive agents
- describe methods and theories for reactive agents, architectures based on subsumption, and potential fields
- describe the physical structure of robots
- account for different degrees of autonomy of robots
- explain concepts, methods and theories of embodied cognition and situatedness
- explain basic concepts, methods and theories of sensing
- explain basic concepts, methods and theories of neural networks and learning
- explain basic concepts, methods and theories of artificial evolution, genetic algorithms, multiple autonomous agents and swarm intelligence
- demonstrate the ability to apply a given subset of the theories, methods and principles discussed during the course

Required Knowledge

To be admitted you must have 60 ECTS-credits in Computing Science/Cognitive Science or 2 years of completed studies, in both cases including a basic programming course (e.g. 5DV104, 5DV105, 5DV106 eller 5DV114) and either Data Structures and Algorithms (5DV108, 5DV127 eller 5DV128) or Application Programming in Python (5DA000) or equivalent.

Proficiency in English equivalent to Swedish upper secondary course English A (IELTS (Academic) with a minimum overall score of 5.5 and no individual score below 5.0. TOEFL PBT (Paper-based Test) with a minimum total score of 530 and a minimum TWE score of 4. TOEFL iBT (Internet-based Test) with a minimum total score of 72 and a minimum score of 17 on the Writing Section).
Where the language of instruction is Swedish, applicants must prove proficiency in Swedish to the level required for basic eligibility for higher studies.

Form of instruction

Education consists of lectures and mandatory computer based assignments. In addition to scheduled activities, individual work with the material is also required.

Examination modes

The examination consists of a written exam in Part 1 and by grading the mandatory computer based assignments in Part 2. In Part 1, the grades given are Fail (U), Pass (3) or Pass with Mark (4), or Pass with Distinction (5). In Part 2 the grades given are Fail (U) or Pass (G). On the course as a whole, the grades given are Fail (U), Pass (3) or Pass with Mark (4), or Pass with Distinction (5). In order to pass the course completely all mandatory parts must be passed as well. The final grade of the course is a summary assessment of the results and decided only after all mandatory parts are passed.

A student who has passed an examination may not be re-examined.

For all students who do not pass the regular examination there is another opportunity to do the examination. A student who has taken two tests for a course or segment of a course, without passing, has the right to have another examiner appointed, unless there exist special reasons (Higher Education Ordinance Chapter 6, section 22). Requests for new examiners are made to the head of the Department of Computing Science.

TRANSFER OF CREDITS
In an exam, this course not be included, in whole or in part, simultaneously with another course of similar content. If in doubt, consult the student counselors at the Department of Computing Science and / or program director of your program.

Note that this course can not be fully accounted for in an examination together with one of the courses Artificially Intelligent Behaviour (5DV084) or Artificial Intelligence (5DV019).

Transfer of credits is considered individually (see the University Code of Rules and regulations for transfer of credits). An application for transfer of credits is made on a special form and should be submitted to the Faculty of Science and Technology, Umeå University.