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

batch normalization

A technique that normalizes a layer's inputs using statistics computed across the current minibatch.

Examples

For a minibatch $z=(1,2,3,4)$ : mean $2.5$ , variance $1.25$ , standardized to about $(-1.34,-0.45,0.45,1.34)$ .