Why is cross entropy loss preferred in classification problems and even in neural network and not mean squared error loss?
Cross entropy loss vs mean squared error loss
hey @nikhil_sarda ,
Cross Entropy is preferred over MSE for classification task as it measures the probability between 0-1 of a class , which is ofcourse better for a classification task.
Whereas , MSE is preferred for regression task as it doesn’t care about what is classes or anything , it just needs to check what the difference is between predicted values and true values.
Yes you can use MSE also for classification , but i don’t think it will perform good.
I hope this would have helped you understand the difference.
Thank You and Happy Coding 
.
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.