Hi there,
I’m wondering why the shape of W^{[1]} is not (4, 1) here?
{moderator edit  quiz question and answers removed}
Thanks in advance!

2 ↩︎
Hi there,
I’m wondering why the shape of W^{[1]} is not (4, 1) here?
{moderator edit  quiz question and answers removed}
Thanks in advance!
2 ↩︎
Because there are 2 inputs and 4 output neurons.
Sorry, but for the output layer, shouldn’t there are 4 inputs and 1 output?
Ah, sorry, my apologies. I didn’t look closely enough at the question. The answer I gave was for W^{[1]}. But for W^{[2]}, note that there are 4 inputs and 1 output. So the dimensions would be 1 x 4, not 4 x 1, right? The math relationship is:
Z^{[2]} = W^{[2]} \cdot A^{[1]} + b^{[2]}
For this network the shape of A^{[1]} will be 4 x m, where m is the number of samples.