MAT-75006 Artificial Intelligence, 7 cr
Additional information
No lectures during 2016-2017. Next implementation round: Spring 2018.
Suitable for postgraduate studies.
The implementation will not be executed during the academic year 2016-2017.
Person responsible
Tapio Elomaa
Lessons
| Implementation | Period | Person responsible | Requirements |
| MAT-75006 2016-01 | - |
Tapio Elomaa |
Learning Outcomes
After completing the course the student will have be familiar with different areas of artificial intelligence. In particular, the student is able to apply to problems arising in application fields the basic methods of solving problems by searching, informed search and exploration, inference in first-order logic, probabilistic reasoning, learning from observations, and statistical learning methods. The student will be able to identify the computational complexity of the used technique. The student will obtain a deeper knowledge on the topic of the chosen study and presentation. Also hands-on experience on some specific artificial intelligence technique will be gathered in a programming home work.
Content
| Content | Core content | Complementary knowledge | Specialist knowledge |
| 1. | Logic, knowledge, and reasoning | propositional and first-order logic | knowledge bases |
| 2. | Problem solving and search | heuristic search | algorithm A* |
| 3. | Uncertain knowledge and reasoning | probabilistic reasoning | decision making |
| 4. | Machine learning | learning from observations | statistical learning |
Instructions for students on how to achieve the learning outcomes
The course grade will be based on the course exam, a study/presentation, and programming home work. Active participation to weekly exercises yields extra points. If the student demonstrates thorough understanding of the core content, s/he may pass the course with grade 3. In order to achieve grade 4, the student must also demonstrate competency in complementary knowledge. The student may achieve grade 5, if s/he also demonstrates good command of specialist knowledge. If there are minor shortcomings regarding the core content, the student may receive the grade 1 or 2, depending on the number of flaws. If there are significant shortcomings regarding core content, the student will not pass the course.
Assessment scale:
Numerical evaluation scale (0-5)
Partial passing:
Study material
| Type | Name | Author | ISBN | URL | Additional information | Examination material |
| Book | Artificial Intelligence: A Modern Approach | Stuart Russell & Peter Norvig | Yes |
Prerequisites
| Course | Mandatory/Advisable | Description |
| MAT-02500 Todennäköisyyslaskenta | Advisable | |
| MAT-02650 Algoritmimatematiikka | Advisable | |
| TIE-02100 Johdatus ohjelmointiin | Mandatory | |
| TIE-02200 Ohjelmoinnin peruskurssi | Advisable |
Correspondence of content
| Course | Corresponds course | Description |
| MAT-75006 Artificial Intelligence, 7 cr | OHJ-2556 Artificial Intelligence, 6 cr |