Diagnostics, Interpretability, Robustness, and Responsible Use

prevent learners from trusting neural networks too quickly.

Units

1. Unit 11.00: Learning curves, confusion matrices, and error slices
2. Unit 11.01: Calibration and confidence caution
3. Unit 11.02: Saliency and attribution as clues, not proof
4. Unit 11.03: Robustness, distribution shift, and out-of-distribution inputs
5. Unit 11.04: Fairness and dataset limitations
6. Unit 11.05: Model cards and responsible release boundaries
7. Unit 11.06: Project step: deep learning review memo

Module work

• Activity
• Knowledge check
• Summary