Re:Learning to write programs that generate images
by nthngnss on Tuesday March 27, 2018 @11:18PM
(#16694966)
Yup, exactly! Btw, didn't realize those were your results (just mindlessly clicked on the link). Very cool stuff!
Re:Learning to write programs that generate images
by Ono-Sendai on Tuesday March 27, 2018 @11:24PM
(#16695000)
Thanks.
The (semi-) obvious next step is to do object/digit recognition with a Bayesian probability calculation, with probabilities bases on this image reconstruction process. In other words, we choose e.g. digits based on how likely they are to have been drawn to give the target image.
I have experimented a little with this idea, but with no successful results so far (plain old NNs still beat it).
Fast painting is a benefit I guess. My search/painting program is very computationally intensive.
Edit: I think I see the point of the paper now. Unguided search is going to be difficult in high-dimensional search spaces like this. So the NNs become a hopefully-effective heuristic guiding the search.