Administrative Information
| Title | Explainable Machine Learning (XAI) |
| Duration | 120 |
| Module | C |
| Lesson Type | Practical |
| Focus | Technical - Future AI |
| Topic | Open Problems and Challenges |
Keywords
XAI,Ante-hoc,Post-hoc,SHAP,LIME,
Learning Goals
- Understand the Taxonomy of XAI techniques
- Understand the advantages and drawbacks of selected approaches to XAI
- Apply selected XAI techniques to a data set
- Identify future directions of XAI
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
Using the tabular example in the notes, using both LIME and SHAP to examine all attributes for four other incorrectly classified instances to describe the predictions. $ Using CNNS and the LIME and SHAP explainability approaches for four other incorrectly classified instances to describe the predictions. $ For a text-based problem, identify four other incorrectly classified instances to describe the predictions and why they may have been incorrect. $ Sum up your efforts, determine if exercises meet all five XAI perspectives, and elaborate if they do.
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.