0% completed

Introduction to AI Fairness

What Is AI Fairness and Why It Matters?Real-Life Examples Formal Definition and Fairness in Regulations

Motivating Example

Credit Scoring Problem Building a Model Is the Model Fair?Challenge: Fairness through Unawareness Quiz on German Scoring Problem

Measuring Fairness

Protected Attributes Space University Example Simpson’s Paradox Group and Individual Fairness A Quick Recap of Common Metrics Demographic Parity Predictive Parity Equality of Opportunity Equalized Odds Effect of Threshold Selection Quiz: Fairness Metrics

Mini Project

Project: Fix Bias Using Threshold Optimization

Mitigation Methods

Data vs. Model Bias

Introduction to Mitigation Methods

More on Threshold Optimization

Adversarial Debiasing

Other Methods and Summary

Quiz: Mitigating Bias

Mini Project

Project: Make a Fair Classifier

Fairness in Natural Language Processing

Word Embeddings Biased Vectors Debiasing Vectors Word Embedding Association Test Data Augmentation Quiz: Fairness in NLP

Mini Project

Project: Explore Fairness in NLP Models

Conclusion

Summary and Next Steps

Course Assessment

Check Your Knowledge About Fair AI

Fundamentals of AI Fairness/

...

/

Reductions

Reductions

Learn how to use reduction methods.

We'll cover the following...

What are reductions?
Usage example

What are reductions?

Reduction approaches take an arbitrary model and attempt to de-bias it according to a selected constraint, commonly demographic parity, equalized odds, or equal opportunity. Still, technically, it can be any other metric. ...