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

activation function

A nonlinear function applied to a neuron's weighted sum, letting a network represent more than a straight line.

Examples

Swapping a hidden layer's activation function from ReLU to sigmoid changes its gradient behavior, not just its output range.