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

He initialization

A weight-variance formula, $\sigma_W^2=2/n$ (fan-in $n$ ), that doubles Xavier's variance to compensate for ReLU zeroing about half its input's variance.

Examples

Fan-in $n=512$ : He's variance is $2/512\approx0.0039$ , double Xavier's $1/512\approx0.00195$ .