NB: I'm not a Stanford student asking for you to do my job, I'm studying online and trying to figure it out by myself.

I'm following Stanford's CS224D and I'm having troubles understanding some of the math.

In the first assignment's solutions, part II question c, I don't understand this part:enter image description here

1) Why does the second derivative has the transpose of W2 ? If I derivate z2 respectively to h, I only get W2 and not the transpose of W2 (Same with the final derivative dCE/dx)

2) I have trouble understanding the logic here. We are derivating CE respectively to z2, then h, then z1. Could someone explain why ?

Any help or link to resources will be much appreciated.

  • $\begingroup$ 1. Transpose due to x and h being row vectors (note that more usually, x and h would be column vectors). Work it out element by element and you'll see. 2. Chain rule. You could instead write it out in one big formula. $\endgroup$ – Mark L. Stone Aug 27 '16 at 14:16

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.