this post was submitted on 28 Dec 2024
750 points (92.6% liked)
196
16773 readers
3605 users here now
Be sure to follow the rule before you head out.
Rule: You must post before you leave.
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
The problem is that the machines are not learning. They are taking a statistical amalgamation of the input images and outputting a selected part of each relevant input (not how people learn or make inferences BTW)
It’s more like a complex selective compression and decompression method than generation of a new image.