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
The schedule will be available no later than one month before the start of the course.
We do not recommend print-outs as changes can occur. At the start of the course,
your department will advise where you can find your schedule during the course.
Note that the course literature can be changed up to two months before the start of the course.
Course reports are displayed for the three most recent course instances.
