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

deep-learning

Sigmoid and tanh

taught

Taught in

Sigmoid, up close
Deep Learning / Neural Networks
Tanh: squashing to between -1 and 1
Deep Learning / Neural Networks

Requires

activation-functions required

Required by

Saturation and gradient behavior required
Side-by-side subplots, titles, legends, and axis labels required
The slope of sigmoid and ReLU required
nn.Sigmoid, nn.ReLU, and nn.Tanh as fixed-formula modules required

Local knowledge map

Local knowledge map

Click to expand

Solid arrows are required prerequisites; dashed are recommended or helpful. Lower rows are more foundational. Click any box to jump to that concept.