Chain rule
The chain rule differentiates a composition by multiplying local derivatives along dependency paths. Reverse-mode automatic differentiation reuses these local derivatives efficiently when a scalar loss depends on many parameters.
(f\circ g)'(x)=f'(g(x))g'(x)
Overview. The chain rule differentiates a composition by multiplying local derivatives along dependency paths.
Context. Reverse-mode automatic differentiation reuses these local derivatives efficiently when a scalar loss depends on many parameters.
Claims and evidence
Claim ledger, 2The chain rule differentiates a composition by multiplying local derivatives along dependency paths.
Reverse-mode automatic differentiation reuses these local derivatives efficiently when a scalar loss depends on many parameters.