Fair Bytes

A technique to explain how black-box machine learning classifiers make predictions

Why many gold-standard computer vision datasets, such as ImageNet, are flawed

Papers, books, and resources to learn about fairness in vision, NLP, and more

An overview of how to use counterfactual fairness to quantify the social bias of crowd workers

Reason #5: Just because you CAN develop an algorithm, doesn’t mean you SHOULD

Despite its impressive performance, the world’s newest language model reflects societal biases in gender, race, and religion

Curricula, projects, and even fiction books to empower students to learn about AI ethics

What does it mean for a machine learning algorithm to be “transparent”?

An overview of how biases against mentions of disabilities are embedded in natural language processing tasks and models