Administrative Information
| Title | XAI Hands-on Assignment |
| Duration | 60 minutes |
| Module | B |
| Lesson Type | Practical |
| Focus | Ethical - Trustworthy AI |
| Topic | General Explainable AI |
Keywords
SHAP, LIME, Explainable AI,
Learning Goals
- Gain experience in implementation of SHAP-model.
- Gain experience in implementation of LIME-model.
- Experience differences (in outcomes) of SHAP vs. LIME
- Reflect on Human-centered application of XAI.
- Experiment with differences in datasets to understand different outcomes of SHAP/LIME (bonus).
Expected Preparation
Learning Events to be Completed Before
Obligatory for Students
- Follow XAI lecture(s)
- Complete Practical Practice with XAI models 1
Optional for Students
None.
References and background for students
None.
Recommended for Teachers
- Solutions are available in the notebook provided.
Lesson materials
Instructions for Teachers
Instructions are provided in the notebook
Outline of lecture
| Duration (min) | Description |
|---|---|
| 0-10 min | Read aim and purpose of exercises and run preparation steps in the notebook. |
| 5-10 min | Excerise 1a: create SHAP model for given dataset/AI-model. |
| 5-10 min | Exercise 1b: reflect on outcomes of SHAP model. |
| 5-10 min | Exercise 2a: create LIME model for same dataset/AI-model. |
| 5-10 min | Exercise 2b: reflect on outcomes of LIME model. |
| 10-15 min | Exercise 3: reflect on differences between LIME and SHAP outcomes, reflect on applicability of LIME vs. SHAP. |
| 10-15 min | Exercise 4: reflect on human-centered aspects of applying XAI (vs. clarifying the AI-model). |
| 10-15min | (Optional) Exercise 5: Experiment with LIME/SHAP-tool to see differences in outcomes from LIME/SHAP. |
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.