Рет қаралды 825
Learn how to find potential sources of bias in data that may lead to an unfair machine learning model. We explore how to quantify unbalanced samples, historical injustice and proxy variables. This is using methods like prevalence, mutual information and feature importance scores. Join us as we navigate the complexities of fairness in machine learning, empowering you to promote equality and inclusivity in AI systems.
*NOTE*: You will now get the XAI course for free if you sign up (not the SHAP course)
SHAP course: adataodyssey.com/courses/shap...
XAI course: adataodyssey.com/courses/xai-...
Newsletter signup: mailchi.mp/40909011987b/signup
Read the companion article (no-paywall link):
towardsdatascience.com/analys...
Other articles you may find useful:
Introduction to Algorithm Fairness: towardsdatascience.com/what-i...
Reasons for Unfairness: towardsdatascience.com/algori...
Correcting Fairness: towardsdatascience.com/approa...
Medium: / conorosullyds
Twitter: / conorosullyds
Mastodon: sigmoid.social/@conorosully
Website: adataodyssey.com/