Deep Learning programme

The 18-week curriculum

Every week opens on its first day. Your place is remembered in this browser, so you can stop and come back.

18weeks
126days

Start here

Pick any week. Week 1 assumes no prior experience.

Phase 1

Foundations

Tensors, autograd, training loops and generalisation
Phase 2

Vision

Convolution, residual networks and transfer learning
Phase 3

Sequences

Recurrence, and the attention that replaced it
Phase 4

Transformers

The architecture, language modelling and pretrained models
Phase 5

Generative and self-supervised

Autoencoders, GANs, diffusion and learning without labels
Phase 6

Production

Keras, making a model cheap, and serving it
Phase 7

Capstone

Your own project, and where to go next

Every week ends with a self-assessment quiz, and each day can be marked complete as you go. Nothing is sent anywhere; your progress lives in this browser only.

Programme detailsAsk a question