Why we are shuffling training examples what is advantage of shuffling them do do this affect training model

#1

why we are shuffling training examples while calculating grad what is advantage of shuffling them do do this affect training model

#2

Hey @hssharma2212000, as you will proceed further with the course, you will see in comming videos, that we perform train-test split. And for that reason we need to perform shuffling.
Suppose dataset contains 100 points, initial 50 points belong to 0 class and last 50 points belong to 1 class. Now when you perform 80-20 split directly than, validation data will contain only 20 points on 1 class. So to prevent this we shuffle the data.

HOpe this resolved your doubt.
Plz mark the doubt as resolved in my doubts section. :blush:

#3

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.