0
$\begingroup$

I am reading the following link : http://blog.manfredas.com/backpropagation-tutorial/ for understanding the derivation of the back propogation algorithm.

enter image description here

In the step for computing the partial derivative of E with respect to w vector, in step 2, the author has directly replaced hw(xi)-yi as sigmoid(xi.w) in the next step.

How are the two equal?

$\endgroup$

1 Answer 1

0
$\begingroup$

The derivative wrt to y_i is 0 because it is constant wrt w and in this case the hypothesis h must be the inner product of the weight and input x passed through a sigmoid.

$\endgroup$
1
  • $\begingroup$ Thank you so much. Just missed to see this, don't know how :) $\endgroup$ Nov 13, 2017 at 17:12

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.