News for hackers. Stuff that matters.
Re:Astronomers explore uses for AI-generated images by amelius on Sunday February 05, 2017 @03:05PM (#13574266)
Interesting article.

However, it leaves me with the question why this process should converge to a desired network. I mean, why doesn't this process generate training artifacts, that get multiplied as the interaction between discriminator and generator progresses?

Re:Astronomers explore uses for AI-generated images by exit on Sunday February 05, 2017 @03:42PM (#13574515)
maybe the complex distribution of "looks like a galaxy" images just isn't that overwhelmingly complex, relative to how cheap computation & storage is nowadays.

what surprises me is how these techniques can structure the space of compressed representations in interesting ways. look at this discussion of thought vectors: https://www.technologyreview.com/s/541356/king-man-woman-que...