Skip to content
Free public beta until December 4, 2026: every course is open, no card needed. After that, the first chapter of each course stays free and full access is a one-time $39 ($19 for up to 100 founding members chosen for helpful feedback). Your progress is kept. How the beta works

language-models

Computing attention by hand on a tiny example

taught

Carrying a 3-token query/key/value example through every step -- $QK^\top$, scaling, softmax, the weighted sum of values -- with real numbers, so the equation in deep-learning's attention chapter has a worked arithmetic anchor before this course's own widget or lab touch it.

Taught in

Requires

  • scaled-dot-product-attention recommended

    deep-learning ch.20 derives the formula and its scaling factor in full; this course's own hand-worked example is the same formula applied, not re-derived.

Required by

Nothing in the catalog needs this yet.

Local knowledge map

Local knowledge map

Click to expand

Solid arrows are required prerequisites; dashed are recommended or helpful. Lower rows are more foundational. Click any box to jump to that concept.