 Solution

ID: past-exam-of-the-mathematics-course-of-the-university-of-cambridge/2021/iii/paper-218/4/a/solution

For hidden layers

h^{(r)} = ϕ_{r} (W_{r} h^{(r - 1)} + b_{r})

with

h^{(0)} = x

, the output logits are

z = W_{R + 1} h^{(R)} + b_{R + 1}

p_{ℓ} (x) = \frac{e ^{z_{ℓ}}}{\sum _{j = 1}^{L} e ^{z_{j}}} .

 New to topics? Read the docs here!