Shouldn’t the loss function be -
-np.mean(y_hot*np.log§ + (1-y_hot)*np.log(1-p))
where p is our prediction matrix
Cost function in binary cross entropy Neural Networks
Hey @raunaqsingh10, the formula you have written is same as binary cross entropy. Which means on backend keras also implement the same thing as written by you.
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.