Thread by @gordic_aleksa

[🧠 collective intelligence 🧠] I've been intrigued by the cellular automata (CA) concept for a long time, and by the potential, mutually beneficial interaction between CAs and deep learning, so I decided to dig a bit deeper. Here are some interesting resources I found:

1/🧵

distill.pub/2020/growing-c… <- one and only Distill. A nice introduction to how neural CA works and how it may be a potentially useful model of morphogenesis and regeneration processes in developmental biology.

@zzznah

2/

(think how we humans are formed from a single egg cell - when and how does this multiplication of cells stop and stays stable?)

3/

arxiv.org/abs/2111.14377 "Collective Intelligence for Deep Learning" <- a recent paper that explores how ideas from collective intelligence (an umbrella term for CA, self-organization, swarm optimization, etc.) have influenced deep learning (and vice versa).

@hardmaru

4/

arxiv.org/abs/2111.13545 "μNCA: Texture Generation with Ultra-Compact Neural Cellular Automata" <- a recent paper that trains a neural CA (compare that to fixed rules of Conway's Game of Life!) to generate interesting textures with as little as 60 bytes of learnable weights!

5/

Finally check out this "upgraded" version of Conway's Game of Life: continuous time-space CA called "Lenia":

1) <- some quick visualizations so that you understand what it's all about (hint: amazing artificial "lifeforms" emerge)

@BertChakovsky

6/

2) <- Lenia explained in a bit more depth

7/

#collectiveintelligence #cellularautomata #deeplearning

Oh, and yeah - neural CA is basically a GNN (as all things should be haha).

In the discrete grid world, every cell (node) has a multidimensional state (feature vector), does some local communication with immediate "pixel neighbors", and outputs a novel cell state.

8/