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

computer-vision

What gradient descent and backpropagation do (primer)

taught

Working-depth-only: training nudges every weight to reduce a loss (gradient descent), and backpropagation is the efficient bookkeeping that computes each weight's nudge via the chain rule -- one sentence of intuition, no derivation.

Taught in

Requires

  • gradient-descent-dl recommended

    deep-learning ch.09 derives gradient descent from the gradient itself; this course's own quizzes only require the working-depth version taught locally.

  • backpropagation recommended

    deep-learning ch.10 derives backpropagation via the chain rule in full; this course's own quizzes only require the working-depth version taught locally.

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.