Explainable AI
The course is an advanced course that focuses on explainability for AI methods.
The course addresses the question of how to explain "black-box" models that are opaque and do not provide any explanation for their inner workings. The course introduces different explainability paradigms, such as post-hoc methods, surrogate models, Shapley values and counterfactual explanations.
The course will cover:
- Intrinsically Interpretable Models
- Global Model-Agnostic Methods
- Local Model-Agnostic Methods
- Optimisation
- Neural Network Interpretability
- Time Series Interpretability
Teaching Format
The teaching activities consist of lectures.
The language of instruction is English.
Assessment
The course is examined through an on-campus written exam and assignments.
Examiner
Study counsellors
Visiting hoursPlease contact us via email if you want to book a meeting. We are available on Campus in Kista and via Zoom.
Phone hoursThursday 12.30–2 pm
Irregular office hoursFirst phone hours for spring 2026: Thursday 15 January
