Part 1 exercises · Machine-learning foundations

All exercises · Part 2

Slides: Parts 1–3 slides

How does a model learn from data? About 20 minutes. Work through the exercises in order; the last one is a short scenario that combines them.

What you will practise

• Name the training signal behind a security task
• See how labels move a score, and what a score does not establish
• Follow a reported email through the pipeline, and find where each stage can fail
• Keep training, validation and test data apart, and choose a model on validation error
• Compute a score by hand and explain why a QR image gets past a text-only filter

Every exercise gives you feedback after you try, and names the slide to look at. You can retry as often as you like, ask for hints, and see the answer after a failed attempt. Your progress is saved only in this browser and is never sent anywhere.