Local derivative

How much one node’s output changes with one of its own inputs, ignoring the rest of the graph.

It starts with ∂L/∂L = 1 and walks back through the graph; at each node it multiplies the gradient arriving from above by that node’s local derivative.
From The chain rule, step “The backward pass”

See it in action

Try local derivative hands-on in the lesson The chain rule, part of the The maths behind AI course.

Open the lesson