Backpropagation Details Pt. 2: Going bonkers with The Chain Rule
StatQuest with Josh Starmer · 13:08
Josh Starmer completes the backpropagation derivation by using the chain rule to compute the derivatives of the sum of the squared residuals (SSR) with respect to the *first-layer* parameters — w₁, b₁, w₂, b₂ — and th...