Sir has told we don’t know real distributionWHY? ,but we are using MNIST dataset so,we know the real images.
Also Sir is telling we need to approximate this without knowing white part.
I think I have not understood plz help.
Generative Adversarial Network GANN
Sir has said that we don’t know the real distribution, which means you have real images in your hand but you still don’t know how can we find new points on that random distribution with those 10 random values in our hand. Hence sir has said that we will estimate this distribution without knowing the white part.
Hope this cleared your doubt. 
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.