Рет қаралды 950
Delve deep into the crucial topic of addressing fairness issues in artificial intelligence. We explore various quantitative approaches to correcting unfair machine learning models:
- Pre-processing,
- In-processing and
- Post-processing
Remember, fairness is a complicated issue that cannot be solved through data and algorithms alone. This is why we also discuss non-quantitative approches to fairness:
- Limiting the use of ML,
- Interpretability,
- Explanations,
- Address the root cause of unfairness,
- Awareness of the problem and
- Team diversity
🚀 Free Course 🚀
*NOTE*: You will now get the XAI course for free if you sign up (not the SHAP course)
SHAP course: adataodyssey.c...
XAI course: adataodyssey.c...
Newsletter signup: mailchi.mp/409...
🚀 Companion Article (no-paywall link): 🚀
towardsdatasci...
🚀Other articles you may find useful 🚀
Introduction to Algorithm Fairness: towardsdatasci...
Reasons for Unfairness: towardsdatasci...
Measuring Fairness: towardsdatasci...
🚀 Get in touch 🚀
Medium: / conorosullyds
Twitter: / conorosullyds
Mastodon: sigmoid.social...
Website: adataodyssey.com/