Administrative Information
| Title | Practice with XAI models 1 |
| Duration | 60 mins |
| Module | B |
| Lesson Type | Practical |
| Focus | Ethical - Trustworthy AI |
| Topic | General Explainable AI |
Keywords
SHAP, Explainable AI,
Learning Goals
- Know how to use SHAP, but also learn some limitations of SHAP
Expected Preparation
Learning Events to be Completed Before
Obligatory for Students
None.
Optional for Students
None.
References and background for students
None.
Recommended for Teachers
None.
Lesson materials
Instructions for Teachers
Exercises to practice with XAI models (SHAP) - AI models pre-provided, so students only have to apply XAI packages.
Datasets can be selected so models might have interesting properties that become apparent when viewed with XAI (a bias that might have ethical concerns).
In this notebook practical, the limits of SHAP are also discussed, and it's difficulty in detecting interaction effects.
Outline
Instructors can choose to let students work individually or in groups on the practical notebook for the entire class (60 mins) or spend time discussing the results immediately in class.
Acknowledgements
The Human-Centered AI Masters programme was Co-Financed by the Connecting Europe Facility of the European Union Under Grant №CEF-TC-2020-1 Digital Skills 2020-EU-IA-0068.