Easier to read with cream paper, a tint, more contrast or larger text? Choose your colours and text, once, for every page.

Free module

Responsible AI

Learn responsible AI hands on: find bias in data, measure fairness, explain predictions, protect privacy and document a model.

5 lessons285 min lessonAI and data science

The lessons

Each lesson is free to read in full. Create a free account to run its commands in a live lab and to sit its quizzes and tasks.

  1. 1 · Container lab

    Where bias in data comes from

    I can find where bias enters a data set by checking its sample, its labels and its history.

    Read the lesson

  2. 2 · Container lab

    How to measure fairness in a model

    I can measure how often a model selects each group and how often it finds the qualified people in each.

    Read the lesson

  3. 3 · Container lab

    Explaining a model's predictions

    I can explain a prediction by changing one input at a time and watching the score move.

    Read the lesson

  4. 4 · Container lab

    Protecting privacy with k-anonymity

    I can find the groups in a table that are too small to keep the people in them private.

    Read the lesson

  5. 5 · Container lab

    Model cards and monitoring a model

    I can document a model on a model card and set a check that tells a named person when it has drifted.

    Read the lesson

Worked in a real lab

Every lesson of this module is worked in a lab started for you alone. The labs it uses:

Teaching a class? Set this module for your students with a teacher guide, marked assignments and a lab for every student.