Additional resources
Instruction and application
In ProgressDive deeper: additional learning materials
If you're interested, use the following resources to continue exploring topics related to this unit.
✨
Fairness metrics & audit workflows:
Explore Fairlearn’s tutorials on computing and visualizing per-group metrics (FNR, FPR) and running bias audits in Python.
✨
Proxy derivation & slicing:
Follow IBM AI Fairness 360’s notebook on deriving demographic proxies and creating disaggregated cohorts.
✨
Output calibration:
Read “On Calibration of Modern Neural Networks” by Guo et al. and try the accompanying temperature-scaling recipes in scikit-learn.
✨
Instance re-weighting strategies:
Browse AIF360’s re-weighing examples to learn how to tune sample weights for fairness without retraining from scratch.
In progress