News for hackers. Stuff that matters.
Re:Learning to write programs that generate images by nthngnss on Tuesday March 27, 2018 @10:41PM (#16694801)
You'd be surprised to see that both "inverse graphics" and "analysis-by-synthesis" are mentioned in the paper
Re:Learning to write programs that generate images by eli_gottlieb on Wednesday March 28, 2018 @02:45PM (#16700552)
Yes, I saw that they are, but at that point, I'd have to ask where the novelty is besides transforming them from probabilistic problems to plain neural-network problems.
Re:Learning to write programs that generate images by nthngnss on Wednesday March 28, 2018 @11:08PM (#16704231)
I would call "inverse graphics" a task. One can solve that task following different strategies. We demonstrate one way that uses RL and GANs and gives reasonably good results. For Omniglot, for example, there are works by Lake et al. that employ probabilistic perspective but the amount of hand-engineering involved makes their approach hard to apply to other tasks