Neural networks
A neural network is a very large pile of multiplications arranged so that adjusting the numbers improves its answers. This course explains the mechanism, the main architectures and why they behave as they do.
What you'll learn
10 chapters, then the quiz
- 01The artificial neuronThe unit everything is built from.
- 02Layers and depthBuilding representations.
- 03How it learnsLoss, gradients and updates.
- 04Activation functionsSmall choices with large effects.
- 05ArchitecturesShapes for different data.
- 06Keeping it generalFighting memorisation.
- 07Training in practiceWhy it is fiddly.
- 08Transfer learningNot starting from scratch.
- 09What they cannot doHonest limitations.
- 10Learning it yourselfA practical path.
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 - Medium
Machine learning basics
Training, testing and the workflow behind a model that actually works.
8 questions8 min