Y
Hacker News
new
|
ask
|
show
|
jobs
by
zozbot234
490 days ago
You can derive the latter information (the joint distribution), given the former and a prior over "all pixels"-like data. So, the defining feature of "generative" models is that they feature a prior over their input data?
2 comments
Nimitz14
490 days ago
Generative models model the data, whether that is p(x) or p(x,y) or (x,y,z) etc.
link
currymj
490 days ago
Yes, though maybe not explicitly written down.
link