Deadlines
- Moodle Reading Mon Dec 6, midnight
- Practice 11 Mon Dec 6, midnight
- Book Ch. 6 — The Ethics of Counting — read for Forum 6, Fri Dec 10 (next week)
- Quiz 6 Fri Dec 3, in class
- Milestone 4 Sat Dec 5, midnight
Week 14: Interpretability Methods
Learning Objectives
- 14A I can apply fairness metrics to compare model performance across demographic subgroups and articulate trade-offs between competing fairness criteria.
- 14B I can use interpretability techniques — feature importance, partial dependence plots, and LIME — to explain model predictions.
Perspectival Reading
Reading: TBD — e.g., Molnar “Interpretable Machine Learning”
Reflection Questions
- Explanation methods produce simplified stories about complex models. When do those stories mislead rather than illuminate?
- Interpretability is often demanded for high-stakes decisions — but by whom, and for whom?
- Can an explanation be technically correct and still be ethically inadequate?