IN9490 ¨C Advanced Topics in Artificial Intelligence for Intelligent Systems

Course content

The course covers various methods within artificial intelligence (AI) and machine learning (ML), and their applications. Examples include algorithms for search, optimization and classification, which to a large extent consist of bio-inspired approaches. Examples of relevant applications include robotics, music, and health and medicine. The course syllabus will continuously be updated with methods from state-of-the-art research. The content is based on presentations from ROBIN group staff, the course participants and invited guests, and will vary depending on who is involved. Students will explore the scientific literature on a selected topic of their interest and proceed to own implementation and conducting thorough experiments under supervision of a ROBIN staff member. The experiments will be disseminated through writing a scientific paper and giving presentations.?

Learning outcome

After taking the course, you will:

• have insight into novel methods (within e.g. evolutionary computation, neural networks, swarm intelligence) used in artificial intelligence (AI) and machine learning (ML)
• have knowledge about how to use AI and ML for various applications
• be able to search for and review literature outlining state-of-the-art within a specific research field.
• be able to critically assess scientific papers and be familiar with the structure of a scientific paper
• be able to design and conduct extensive experiments using AI and ML, with emphasis on evaluation
• have experience in presenting scientific work to others
• have experience in writing a scientific paper at a level suitable for publication at a relevant conference or journal?

Admission to the course

The course is limited to 5 students (25 in IN5490 and 5 in IN9490, 30 in total). If the number of enrolled students is higher than the limit, they will be ranked as follows:

1. PhD candidates affiliated to ROBIN and/or RITMO who have the course approved in their study plan and who will do research including AI/ML
2. PhD candidates affiliated to the Department of Informatics or AUTOSENS who have the course approved in their study plan and who will do research including AI/ML
3. PhD candidates with other affiliations at UiO who have the course approved in their study plan and who will do research including AI/ML
4. Others

Recommended previous knowledge

IN3050 ¨C Introduction to Artificial Intelligence and Machine Learning/IN4050 ¨C Introduction to Artificial Intelligence and Machine Learning, INF3490 ¨C Biologically inspired computing (continued)/INF4490 ¨C Biologically Inspired Computing (continued) or similar

Overlapping courses

• 10 credits overlap with IN5490 ¨C Advanced Topics in Artificial Intelligence for Intelligent Systems.
• 5 credits overlap with IN9495 ¨C Advanced Topics in Artificial Intelligence for Intelligent Systems (continued).

Teaching

The course material is taught through lectures, discussions, supervision, and assignments. Lectures and student presentations will be organised as two- or three-week workshop sessions. Teaching is combined with IN5490. Project work is done in groups in between the workshop weeks and will be guided by a group supervisor who is an expert on the chosen topic.

80% workshop sessions (lectures, discussions etc) attendance is required, and the students must be active in discussions and give at least one paper summary presentation and one or more presentation(s) of their project. There are mandatory assignments/tasks that must be approved.?Mandatory assignments and other hand-ins at Department of Informatics during the pandemic?

Examination

To pass, the following requirements need to be fulfilled throughout the semester:

• Students must give at least one paper summary presentation.
• Prepare one paper draft?and get approved compulsory assignments. Equal contribution of each project member in a group is expected, otherwise, additional assignments may have to be passed.
• Attend at least 80% of all seminar sessions.

The paper draft will consist of a?more thorough?set of experiments?and a 50% longer paper compared to IN5490, and assignments of the?PhD-students will entail?additional work compared to IN5490.

It will also be counted as one of?your three?attempts to sit the exam for this course, if you sit the exam for one of the following courses: IN5490 ¨C Advanced Topics in Artificial Intelligence for Intelligent Systems

Language of examination

The examination text is given in English, and you submit your response in English.

Grading scale

Grades are awarded on a pass/fail scale. Read more about the grading system.

Resit an examination

Students who can document a valid reason for absence from the regular examination are offered a postponed examination at the beginning of the next semester. Re-scheduled examinations are not offered to students who withdraw during, or did not pass the original examination.

More about examinations at UiO

• Use of sources and citations
• Special exam arrangements due to individual needs
• Withdrawal from an exam
• Illness at exams / postponed exams
• Explanation of grades and appeals
• Resitting an exam
• Cheating/attempted cheating

You will find further guides and resources at the web page on examinations at UiO.