Fairness in AI

Adversarial Debiasing is a technique to reduce bias in machine learning models using adversarial training.

In-Processing Fairness ensures AI decisions remain unbiased during data processing.

Model fairness ensures AI systems make unbiased decisions, promoting equality and ethical standards in AI applications.

Post-Processing Fairness ensures AI outcomes are fair after initial predictions are made.

Predictive Parity ensures that a model's predictions are equally accurate across different groups.