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

RMSNorm

Layer normalization with the mean-subtraction step dropped: rescale by the root mean square, $\text{RMS}(z)=\sqrt{\frac1d\sum z_k^2}$ , instead of by the standard deviation.

Examples

For $z=(2,8,5,11)$ : $\text{RMS}(z)=\sqrt{53.5}\approx7.31$ , giving $z/\text{RMS}(z)\approx(0.27,1.10,0.68,1.51)$ .