Machine learning basics
Understanding AI covers what these systems are. This course covers how one is actually built: the workflow from a question to a model that holds up on data it has never seen.
What you'll learn
10 chapters, then the quiz
- 01Framing the problemBefore any code.
- 02DataWhere most of the work happens.
- 03Training and testingHonest evaluation.
- 04Underfitting and overfittingTwo ways to be wrong.
- 05Measuring performanceChoosing the right number.
- 06Common algorithmsA short tour.
- 07How training worksLoss and gradient descent.
- 08The pipelineFrom raw data to a prediction.
- 09After deploymentWhere models quietly rot.
- 10Common pitfallsHow projects fail.
More ai & data tests
See all →- Easy
Understanding AI
What machine learning actually does, what a language model is, and where both fall down.
8 questions7 min - Medium
Data analysis
Averages, spread, correlation and the traps that make numbers say the wrong thing.
8 questions7 min - Hard
Neural networks
Layers, weights and backpropagation, explained without the linear algebra.
8 questions8 min