Suppose we have been given a dataset with only one point (x,y) in it. We will now define a new loss function known as the cross entropy loss function as follows : L(w,b) = -y*log(f(x)), where f(x) is the logistic function with parameters W and B. Note that y is the true value given x whereas f(x) is the output of the model given x as the input. What will be the partial derivative of the cross entropy loss function with respect to W and B. Let ‘M’ be the partial derivative with respect to ‘W’ and ‘N’ be that with respect to ‘B’ then
QUIZ_Neural network
Hey @rajukumarbhui, here is the solution,
Hope this resolved your doubt.
Plz mark the doubt as resolved in my doubts section. 
I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.
On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.