Neural Cellular Automata Can Respond to Signals

May 22, 2023 · Entered Twilight · 🏛 The 2023 Conference on Artificial Life

Repo contents: ExternalSignals.ipynb, InternalSignals.ipynb, README.md, gecko_colourchange_model.zip, gecko_legs, gecko_legs_model.zip, geckos, hearts

Authors James Stovold arXiv ID 2305.12971 Category cs.NE: Neural & Evolutionary Cross-listed cs.AI, cs.DC, cs.LG Citations 7 Venue The 2023 Conference on Artificial Life Repository https://github.com/jstovold/ALIFE2023 ⭐ 4 Last Checked 6 months ago

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