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

backward pass

The second sweep through a computational graph, running from the loss back to every leaf, that computes each node's gradient.

Examples

The forward pass computes $\hat y\approx0.6131$ ; the backward pass then computes all nine parameter gradients from that same graph, walked in reverse.