Build Track

Build Track

A parallel, hands-on thread that runs alongside the lessons. Each build takes one idea from the course and makes it physical: you write the mechanism yourself, in numpy and the standard library, and watch it work.

how to use this The Build Track is optional and depth-by-choice. Conceptual progress through the course never requires a build: you can read every lesson, pass every synthesis and calibration, and skip the builds entirely. The builds are here for when you want to feel an idea rather than just read it. Do them now, do them later, or skip them and carry on.

Live builds

Five builds are ready. Each attaches to the lesson that supplies its idea and rejoins the course straight afterwards, so a build never pulls you off the main path.

B0

Inventory your kit

After L0 · about 30 to 60 min

Catalogue the hardware you actually have (CPU, RAM, any GPU or boards) in a short markdown file. The baseline every later build measures against.

B1

Tabular Q-learning agent on gridworld

After L6 · about 3 hours

A Q-learning agent that learns to cross a 5 by 5 gridworld with a literal Q-table, no neural net. Watch a policy form from reward alone.

B2

Tokenizer explorer

After L8 · about 2.5 to 3 hours

Build a minimal byte-pair-encoding tokenizer by hand: count pairs, merge the most frequent, encode and decode, and compare characters-per-token across languages and code.

B3

Vector playground

After L12 · about 2 to 2.5 hours

Load pretrained word vectors as data and build the geometry by hand: cosine similarity, nearest neighbours, analogy arithmetic, and a 2D scatter.

B4

Gradient descent visualiser

After L19 · about 2 to 2.5 hours

Derive a 2D loss surface's gradient, hand-write the descent update, and plot the optimiser's path over contours while you sweep learning rate and momentum.

Coming as the course continues

The Build Track runs to B17. Later builds unlock as the course reaches the lessons they depend on, so they are not linked yet. They are listed here so you can see the shape of the track: numpy-first implementations of the core machinery, then local deployment.

support Builds lean on a small set of Tooling references for setup and Python recall: the Tooling hub collects them. The syllabus shows where each build sits in the course.