Why do we normalise the data?
Normalising the data
hey @nikhil_sarda ,
Its basically a way to reach convergence faster and more closer to global minima.
Many models assume the input data to have some characteristics like mean to 0 and std. to be as 1 ,
hence for them this normalization comes in better way.
Similarly, for other models too , based on experiments it is seen that it works good.
But there is hard rule that you need to normalize the data everytime ,
its a kind of feature processing , and you need to practice and perform a lot of experiments to understand it usecase.
I hope this helps.
THank You 
.
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.