Fairness

Estimated Time: 5 minutes

Learning Objectives

• Become aware of common human biases that can inadvertently be reproduced by ML algorithms.
• Proactively explore data to identify sources of bias before training a model
• Evaluate model predictions for bias

Evaluating a machine learning model responsibly requires doing more than just calculating loss metrics. Before putting a model into production, it's critical to audit training data and evaluate predictions for bias.

This module looks at different types of human biases that can manifest in training data. It then provides strategies to identify them and evaluate their effects.

Fairness

What do you see?

What do you see?

• Bananas

What do you see?

• Bananas
• Stickers

What do you see?

• Bananas
• Stickers
• Bananas on shelves

What do you see?

• Green Bananas
• Unripe Bananas

What do you see?

• Overripe Bananas
• Good for Banana Bread

What do you see?

Yellow Bananas

Yellow is prototypical for bananas

Designing for Fairness

Designing for Fairness

1. Consider the problem

Designing for Fairness

1. Consider the problem
2. Ask experts

Designing for Fairness

1. Consider the problem
2. Ask experts
3. Train the models to account for bias

Designing for Fairness

1. Consider the problem
2. Ask experts
3. Train the models to account for bias
4. Interpret outcomes

Designing for Fairness

1. Consider the problem
2. Ask experts
3. Train the models to account for bias
4. Interpret outcomes
5. Publish with context

Help Center