Some online resources relevant to the topics of fairness, accountability and transparency in machine learning.
- UC Berkeley CS294: Fairness in Machine Learning course.
- NIPS 2017 tutorial on fairness in ML: slides and video.
- Attacking discrimination with smarter machine learning.
- CMU ece734 course – this slides in particular.
- Fairness by privacy is not possible: It’s Not Privacy, and It’s Not Fair.
- There’s a FAT* 2018 tutorial on algorithmic fairness (associate code is available here: BlackBoxAuditing) – see this blog post.
- NorthPoint vs. ProPublica article about the COMPAS:
- “As Gummadi points out, ProPublica compared false positive rates and false negative rates for blacks and whites and found them to be skewed in favor of whites. Northpointe, in contrast, compared the PPVs for different races and found them to be similar. In part because the recidivism rates for blacks and whites do in fact differ, it is mathematically likely that the positive predictive values for people in each group will be similar while the rates of false negatives are not.”