Neural Cellular Automata Can Respond to Signals

James Stovold
5/22/2023
cs.NEcs.AIcs.DC

Official code: jstovold/ALIFE2023 (4 stars, last commit 2023-05-14).

Abstract

Neural Cellular Automata (NCAs) are a model of morphogenesis, capable of growing two-dimensional artificial organisms from a single seed cell. In this paper, we show that NCAs can be trained to respond to signals. Two types of signal are used: internal (genomically-coded) signals, and external (environmental) signals. Signals are presented to a single pixel for a single timestep. Results show NCAs are able to grow into multiple distinct forms based on internal signals, and are able to change colour based on external signals. Overall these contribute to the development of NCAs as a model of artificial morphogenesis, and pave the way for future developments embedding dynamic behaviour into the NCA model. Code and target images are available through GitHub: https://github.com/jstovold/ALIFE2023

View on arXivView PDF

Code Implementations(1)

jstovold/ALIFE2023Official100%
41Jupyter Notebook3 years ago

Cite this paper

@article{stovold2023neural,
  title  = {Neural Cellular Automata Can Respond to Signals},
  author = {James Stovold},
  year   = {2023},
  eprint = {2305.12971},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.12971v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.12971.svg)](https://codeofpaper.com/paper/2305.12971)

Discussion