Rendered at 14:49:42 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
zcw100 13 minutes ago [-]
I've always loved the original work and it's nice to see they're still working on it. I've always wondered if there was a way to connect this back to infrastructure rather than images. Something you could run on a cluster and if portions of it failed it would regenerate the system.
whilenot-dev 3 hours ago [-]
The automata just completely destroys the image if I draw too much over the stabilized image with the brush. 5 horizontal swipes are enough to destroy the kitty, is that to be expected?
The NeuralCA both generates and maintains the pattern. Because the NCA was not exposed to damage or erasure during training, its regeneration capability is a purely emergent phenomenon. However, this ability remains somewhat brittle, particularly when the central regions of the pattern are erased.
mackenney 2 hours ago [-]
I would love to see two seeds competing for space in the grid
WhiteNoiz3 2 hours ago [-]
With the old model (and I suspect this one too) it's trained to generate from a single 'seed' pixel in the center of the image. If you erase the center of the image, that's when it completely collapses.
oersted 30 minutes ago [-]
It must be more general than that, otherwise the cells wouldn’t be able to repair their area if the damage came from the wrong direction (repair is not center-out).
The model generally learns to generate each pixel from its surroundings, even if the surroundings are partially missing.
WhiteNoiz3 25 minutes ago [-]
There's hidden state in the model which presumably it uses to communicate position, ie there's the 3 colors but then a bunch of other channels that the model can use how it wants.
cl3misch 36 minutes ago [-]
Have you actually tried that? If you specifically erase the center, the image does change a lot at first, but rebuilds itself eventually (albeit to a slightly different final state). It's uncanny how "biological" is feels!
WhiteNoiz3 24 minutes ago [-]
I have yes.. You need to erase a larger amount of the center, but it almost always results in a collapse wheras erasing around the center typically regrows.
Mithriil 27 minutes ago [-]
If you hold the eraser for a second at the center, I find that it destroys the image more often than not.
WhitneyLand 1 hours ago [-]
At a glance it looks like it could be just iterative texture sampling.
The difference is when creating each pixel, there’s no coordinate to look up, instead it’s using only a set of rules like Conway’s game of life.
But the rules come from a neural network trained on the image, so… it’s kind of memorizing enough information to effectively do the same thing as texture sampling, but using only local information.
I’m sure I’m missing something about how it works or what makes it interesting…
oersted 42 minutes ago [-]
To me, it is intriguing as a toy model for how cells are able to grow into complex tissue and organisms based only on local information, and how they are able to repair and recover harmed tissue.
Of course, this is as close to cells, as neurons from neural networks are to real neurons. And I have no idea what it could be applied to (inpainting/outpainting?), but it’s interesting as exploratory research.
esychology 11 minutes ago [-]
[flagged]
hidelooktropic 2 hours ago [-]
For the unfamiliar, could someone explain what I'm looking at? The abstract was a little too concrete (heh) for me to follow.
esychology 2 hours ago [-]
If you're familiar with CAs (e.g. Conway's Game of Life), you can think of a NeuralCA as a CA where the update rule is given by a neural network. Here we optimize the neural net weights so that it behaves a certain way (e.g. grow a lizard from a single seed).
flir 2 hours ago [-]
What are the inputs to the NN? The whole grid, or just nearby cells? What happens if two NNs overlap on the same grid? (Gonna go read the paper).
esychology 2 hours ago [-]
The input to the NN is just the 3x3 neighborhood around a cell.
We can overlap two NNs on the same grid (through interpolation). Checkout https://meshnca.github.io
to see the effect. When the brush is in graft mode, it basically allows you to paint some regions that will follow a different NN rule.
flir 2 hours ago [-]
> The input to the NN is just the 3x3 neighborhood around a cell.
Well that sounds like black magic. Nice. Thanks for the reply.
The abstract implies that strictly local updates are a hinderance to high res, however i would have thought there would be an interesting way to get speed up gains from neighbor-only traffic on GPUs CAM-style. am i making that up?
esychology 2 hours ago [-]
I think performance is not the only issue for scaling to larger grids. CUDA Convolution implementation already utilizes coalescing to improve performance.
The main bottleneck is that in larger grids, cells are further apart, and it takes more steps for them to be able to communicate.
embedding-shape 3 hours ago [-]
Really interesting demo, nicely done :) Would be fun if switching the "Target Image" when using the second brush mode in the Growing Demo didn't erase/reset the existing canvas, so we could "stamp" new things on top of other images. Small thing perhaps but I got sad when it disappeared when I wanted to merge a kitten on top of the chameleon but couldn't :(
esychology 7 minutes ago [-]
That's not possible in the current demo but this sounds like an interesting feature to work on and add!
bfmalky 2 hours ago [-]
You can, just enable the 'transition' switch.
embedding-shape 40 minutes ago [-]
That seems to be something else? It takes the current image and "transforms" it into the new target.
WithinReason 4 hours ago [-]
You can make the centipede grow longer, which makes sense given how this works. Or grow a 2nd centipede for extra points.
esychology 4 hours ago [-]
haha yes, also the same with the worm
amelius 4 hours ago [-]
Why are the images always generated in the same orientation (upright)? Do the cells have awareness of what is "up"?
WhiteNoiz3 19 minutes ago [-]
IIRC training starts with the initial state and the end state, and the end state is always oriented the same way. It would be interesting to see what would happen if the end state was rotated randomly though I suspect it wouldn't work so well.
esychology 4 hours ago [-]
yeah normally NCAs have a sense of up and left. There are some isotropic variants that make the perception fully rotation-invariant.
mirekrusin 3 hours ago [-]
So the goal is to evaporate it with minimum number of shots?
EDIT: video here: https://imgur.com/a/ItZGd5X
The model generally learns to generate each pixel from its surroundings, even if the surroundings are partially missing.
The difference is when creating each pixel, there’s no coordinate to look up, instead it’s using only a set of rules like Conway’s game of life.
But the rules come from a neural network trained on the image, so… it’s kind of memorizing enough information to effectively do the same thing as texture sampling, but using only local information.
I’m sure I’m missing something about how it works or what makes it interesting…
Of course, this is as close to cells, as neurons from neural networks are to real neurons. And I have no idea what it could be applied to (inpainting/outpainting?), but it’s interesting as exploratory research.
Well that sounds like black magic. Nice. Thanks for the reply.