Course syllabus - Trustworthy Artificial Intelligence

Objectives

This course introduces concepts and relevant problems where trustworthiness in developing AI systems is crucial. The purpose is to enable the students to critically evaluate existing AI methods, techniques and algorithms to increase explainability, transparency, fairness and trust in AI systems. 

Learning outcomes

After completing the course, the student shall be able to: 

1. describe and understand the fundamentals of trustworthy AI,
2. demonstrate the ability to apply XAI methods and algorithms and
3. describe and understand the challenges and measures of fair ML.  

Course content

- Introduction to trustworthiness in AI: fundamental concept, requirements, challenges, and limitations.  

- Explainable AI: definition, requirements and methods.  

- Algorithmic Fairness: Data bias, Ethics, Fair ML. 

Specific requirements

90 credits of which at least 60 credits in Computer Science or equivalent, including 15 credits in programming as well as 2,5 credits in basic probability theory and 2,5 credits in linear algebra, or equivalent.  In addition, Swedish course B/Swedish course 3 and English course A/English course 6 are required. For courses given entirely in English exemption is made from the requirement in Swedish course B/Swedish course 3. 

Examination

Assignment (INL1) 0.5 credits, examines the learning outcome 1, marks Fail (U) or Pass (G). 

Exercise (OVN1), 2.0 credits, examines the learning outcomes 2-3, marks Fail (U) or Pass (G). 

A student who has a certificate from MDU regarding a disability has the opportunity to submit a request for supportive measures during written examinations or other forms of examination, in accordance with the Rules and Regulations for Examinations at First-cycle and Second-cycle Level at Mälardalen University (2020/1655). It is the examiner who takes decisions on any supportive measures, based on what kind of certificate is issued, and in that case which measures are to be applied.

Suspicions of attempting to deceive in examinations (cheating) are reported to the Vice-Chancellor, in accordance with the Higher Education Ordinance, and are examined by the University’s Disciplinary Board. If the Disciplinary Board considers the student to be guilty of a disciplinary offence, the Board will take a decision on disciplinary action, which will be a warning or suspension.

Grade

Two-grade scale