Neural Cellular Automata Can Respond to Signals

Stovold, James (2023) Neural Cellular Automata Can Respond to Signals. In: ALIFE 2023: Ghost in the Machine: : Proceedings of the 2023 Artificial Life Conference. MIT Press, Cambridge, Mass..

[thumbnail of Neural Cellular Automata Can Respond to Signals]
Text (Neural Cellular Automata Can Respond to Signals) - Published Version
Available under License Creative Commons Attribution.

Download (0B)
[thumbnail of Neural Cellular Automata Can Respond to Signals]
Text (Neural Cellular Automata Can Respond to Signals) - Published Version
Available under License Creative Commons Attribution.

Download (0B)
[thumbnail of Neural Cellular Automata Can Respond to Signals]
Text (Neural Cellular Automata Can Respond to Signals) - Published Version
Available under License Creative Commons Attribution.

Download (0B)
[thumbnail of Neural Cellular Automata Can Respond to Signals]
Text (Neural Cellular Automata Can Respond to Signals)
isal_a_00567.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (6MB)

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

Item Type:
Contribution in Book/Report/Proceedings
Uncontrolled Keywords:
Research Output Funding/no_not_funded
Subjects:
?? no - not fundedno ??
ID Code:
215344
Deposited By:
Deposited On:
28 May 2024 15:15
Refereed?:
Yes
Published?:
Published
Last Modified:
28 May 2024 15:15