https://pair.withgoogle.com/explorables/

PAIR Logo
Guidebook Explorables Tools Research Events [logo-mediu]
AI Explorables

Big ideas in machine learning, simply explained

The rapidly increasing usage of machine learning raises complicated
questions: How can we tell if models are fair? Why do models make the
predictions that they do? What are the privacy implications of
feeding enormous amounts of data into models?

This ongoing series of interactive, formula-free essays will walk you
through these important concepts.

[pair-sub-e]
[inside-fla]
[measuring-]

Measuring Diversity

Search results that reflect historic inequities can amplify
stereotypes and perpetuate under-representation. Carefully measuring
diversity in data sets can help.

[arrow-link]Start exploring
[model-inve]

Why Some Models Leak Data

Machine learning models use large amounts of data, some of which can
be sensitive. If they're not trained correctly, sometimes that data
is inadvertently revealed.

[arrow-link]Start exploring
[explorable]

Collecting Sensitive Information

The availability of giant datasets and faster computers is making it
harder to collect and study private information without inadvertently
violating people's privacy.

[arrow-link]Start exploring
[explorable]

Hidden Bias

Models trained on real-world data can encode real-world bias. Hiding
information about protected classes doesn't always fix things --
sometimes it can even hurt.

[arrow-link]Start exploring
[explorable]

Measuring Fairness

There are multiple ways to measure accuracy. No matter how we build
our model, accuracy across these measures will vary when applied to
different groups of people.

[arrow-link]Start exploring
[inside-fla]
Google Logo
Google Research Google Design
[mail] [github] [medium] [youtube]
Google Logo