Open Questions about Generative Adversarial Networks

Re:Open Questions about Generative Adversarial Networks by genai on Tuesday April 09, 2019 @11:21PM (#19621513)

How would you even prove “derivative work”? My understanding is that in proving derivative work you would need to show the original, but in a GAN output which could be made up of 20MM nodes you would not even be able to confirm which 200K image(s) where used in the production of the output result

[ Parent | on HN ]

Re:Open Questions about Generative Adversarial Networks by tasdfqwer0897 on Tuesday April 09, 2019 @11:25PM (#19621546)

This actually might have interesting connections to ideas from differential privacy.

Maybe the work is derivative of a particular training image if we can easily predict the presence or absence of that training image given only the trained model?

[ Parent | on HN ]

Re:Open Questions about Generative Adversarial Networks by genai on Tuesday April 09, 2019 @11:56PM (#19621699)

If you load 50k celebrity images into a tensor of size (500000, 28, 28, 3) and then generate a resulting tensor that results in a (28, 28, 3) tensor where each of the pixel locations is merged to form an average face image (similar to https://www.dailymail.co.uk/femail/article-1355521/Average-f... ), then although the trained model contains all the images; I would have thought the output average face image is an entirely new creative work?

[ Parent | on HN ]