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

gradient descent

The update rule w \leftarrow w - \eta L'(w) (or its gradient version for several parameters): repeatedly move every parameter a small distance against its own slope, so the loss keeps falling.

Examples

  • On L(w)=(w-3)^2 from w_0=0 with \eta=0.1: w moves 0, 0.6, 1.08, 1.464, \ldots, toward the minimum at w=3.

See also

learning rate gradient
Read the full section →
Graph settings

Calculator