News for hackers. Stuff that matters.
Re:Recurrent Neural Network Tutorial for Artists (2017) by sabertoothed on Monday April 16, 2018 @12:06PM (#16849995)
Hi jefft255,

I think you are totally right. As far as I understand, CNNs rely on the correlation of neighbouring pixels. And so directly applying them to vector graphics won't work.

However, vectorisation has massive downsides as well.

I will try to summarise it in some article. This had nerd-sniped my brain and so I need to write it down. Even if I have no solution for the problem yet.

Happy to send you a link to the draft once I have it so you can comment.

Re:Recurrent Neural Network Tutorial for Artists (2017) by kevinwang on Monday April 16, 2018 @03:39PM (#16852037)
In my pretty untrained opinion, it feels like something that outputs vector images might well be trained using reinforcement learning, since it seems like the problem can be well modeled with a policy: "given what I want to produce and what I've produced so far, the next vector object I want to draw is x"