AIMaks
Sign inBegin intake
Animationsbackpropagation

Backpropagation Explained

The chain rule in action — watch gradients flow backward through a computation graph to update weights during training.

intermediate50s4 frames · step through
BackpropagationThe chain rule in actionx×w+bLStep through to see gradients flow backward
Frame 1 of 4
\frac{\partial L}{\partial w} = \frac{\partial L}{\partial \hat{y}} \cdot \frac{\partial \hat{y}}{\partial z} \cdot \frac{\partial z}{\partial w}

Backpropagation: How Networks Learn