Admission requirements
Enrolment is restricted to a limited number of Master students, who preferably follow other courses related to artificial intelligence (including deep learning, machine learning, optimisation, planning and scheduling, multi-agent systems and other areas of AI).
Assumed prior knowledge
It is assumed that the student has
Good knowledge of Artificial Intelligence and Machine Learning techniques (see for example the content of the courses 'Data Science', 'Machine Learning' and 'Symbolic AI')
Familiarity with deep learning (see 'Introduction to Deep Learning' -- should be followed prior to this course)
Students are discouraged to follow this course in the first semester of the program
Description
While in the past, performance has been the main focus of much work in artificial intelligence (AI), aspects of trustworthiness safety are increasingly recognised as similarly significant.
This seminar course on trustworthy artificial intelligence aims to develop a deeper insight into various aspects of trustworthy AI.
Students will work in groups of two on a range of topics from trustworthy artificial intelligence, which spans the robustness and verification of AI methods, including - but not restricted to - neural networks; the explainability and interpretability of the results obtained from AI algorithms; as well as bias and privacy issues in machine learning.
Each group will be assigned recently published work from the research literature, which will serve as the starting point for an in-depth investigation of a specific topic; the results of this investigation will be presented in class and compiled into a report. By presenting the results of the topic in class, other students will be informed about the findings, and learn about all topics that are in scope.
Course objectives
The first lecture will be an introduction by the lecturer. Afterwards, the students will be divided into groups of two, where they will work on a certain topic related to trustworthy artificial intelligence.
After the course, students should be able to
understand the various topics and aspects of trustworthy artificial intelligence (in particular the seven aspects formulated by the European Commission)
critically evaluate the literature on a specific topic from trustworthy artificial intelligence
apply existing methods to novel problem instances (in particular formal verification of robustness properties)
disseminate obtained knowledge in a comprehensible way (using the following forms: presentation, interaction and report writing)
See Bloom’s taxonomy for a further explanation of the required level of understanding per item.
Timetable
You will find the timetables for all courses and degree programmes of Leiden University in the tool MyTimetable (login). Any teaching activities that you have sucessfully registered for in MyStudyMap will automatically be displayed in MyTimeTable. Any timetables that you add manually, will be saved and automatically displayed the next time you sign in.
MyTimetable allows you to integrate your timetable with your calendar apps such as Outlook, Google Calendar, Apple Calendar and other calendar apps on your smartphone. Any timetable changes will be automatically synced with your calendar. If you wish, you can also receive an email notification of the change. You can turn notifications on in ‘Settings’ (after login).
For more information, watch the video or go the the 'help-page' in MyTimetable. Please note: Joint Degree students Leiden/Delft have to merge their two different timetables into one. This video explains how to do this.
Mode of instruction
Seminar (content will be provided through student presentations & discussions)
Final conference (on which we will present the results to each other)
Course load
Total hours of study: 168 hrs. (= 6 EC)
The time will be divided between:
Preparing the lectures
- read the papers from the literature to engage in discussions
- once: prepare to present a paper
Attending the lectures (mandatory)
Peer review, giving critical but constructive feedback to fellow-students
Final conference, on which the results will be presented
Group work is an integral part of the course. You will be expected to complete the assignments together with a team mate.
Assessment method
The students will write a scientific report that surveys the literature on a selected topic from the field of trustworthy artificial intelligence, accounting for 80% of the grade. Throughout the semester, students can obtain feedback on their progress. It will be presented to their fellow students at the final conference (20% of the grade). In both cases, an important aspect of the grade is the comprehensibility to fellow students. The final report should have a passing grade in order to complete the course.
Reading list
Recent and seminal overview papers from the Trustworthy Artificial Intelligence literature.
Registration
Every student has to register for courses with the enrollment tool MyStudyMap. There are two registration periods per year: registration for the fall semester opens in July and registration for the spring semester opens in December. Please see this page for more information.
Please note that it is compulsory to both preregister and confirm your participation for every exam and retake. Not being registered for a course means that you are not allowed to participate in the final exam of the course. Confirming your exam participation is possible until ten days before the exam.
Extensive FAQ's on MyStudymap can be found here.
Contact
Lecturers: dr. J.N. van Rijn
Remarks
More information will be available on the dedicated website for this course, hosted on BrightSpace.