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

weight decay

A regularization technique that shrinks parameters toward zero during training, discouraging overly large weights.

Examples

Adding $\lambda\|w\|^2$ to the loss penalizes large weights, nudging every update slightly back toward zero.