Show HN: Neural Particle Automata

eesychology about 4 hours ago 7 commentsRead Article on selforg-npa.github.io

RU version is available. Content is displayed in original English for accuracy.

Neural CAs model self-organizing pattern formation on grids. Now the grid is gone. Each cell is an agentic particle that can move freely in space and change its state.

While each particle follows a simple shared rule, many together can grow complex morphologies or form intricate patterns. The resulting particle system as a whole can regenerate from damage and exhibits surprising emergent behavior.

Try cutting the lizard and watch it heal itself!

⚡ Community Insights

Discussion Sentiment

86% Positive

Analyzed from 156 words in the discussion.

Discussion (7 Comments)Read Original on HackerNews

Jgoauh•15 minutes ago

could something similar be used for texture synthesis ? of course the particles will need to be arranged in a grid and everything, or maybe recreate the texture by interpolating between the particles to exploit low contrast areas in the data

sixeyes•about 1 hour ago

Found it much interesting that i could mess up a pattern enough that it couldn't re-form.

Would be fun if selecting a new pattern didn't refresh the image as it is. Although maybe that's a requirement?

patcon•7 minutes ago

Agree! This reminded me of a post that tweaked my brain a few months ago :)

https://open.substack.com/pub/defenderofthebasic/p/why-does-...

Also reminds me of Dr Michael Levin's work, which is living rent free in my brain lately

mattdesl•about 2 hours ago

This is super cool, great work. Is there a video or demo of the 3D point cloud "gaussian splat" like experiments?

afrodisiac•about 3 hours ago

Super cool work!!! Do you think it would be possible to do something like cell division here?

treyd•17 minutes ago

If you look at the texture demo with the zeros, it looks a bit like lipid membranes merging/splitting as they stabilize more or less around a particular size.

esychology•about 3 hours ago

Thanks! Yeah I think it should be possible though it requires making the cell division/splitting a differentiable operation. But nontheless, this is indeed a very interesting and promising direction to pursue.