← Back to all news
arXiv Machine Learning By Sanyam Jain, Felix Simon Reimers, Stefano Nichele

Self-Replicating Neural Cellular Automata: Quantifying Emergent Phenotypic and Genotypic Diversity in an OpenEnded Substrate

Read the original on arXiv Machine Learning →

The paper investigates a cellular‑automata substrate where each pixel hosts a tiny neural network that senses its neighbors and survives only by self‑replication with mutated weights. Starting from a few founders, the system evolves into a spatially organized ecosystem of competing species, and the authors introduce coarse‑grained metrics to quantify phenotypic and genotypic diversity at two scales. Experiments show that high phenotypic diversity reduces genotypic diversity and vice versa, and that full‑genome hash colouring reveals lineage structures missed by random‑weight probes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 25

On Growth and Form, and Function: Reusable Regulatory Handles Control Phenotypic Variation

The study investigates how phenotypic changes can be encoded as low‑dimensional modulations of a self‑organizing developmental system, using neural cellular automata (NCAs) as a model. By applying low‑rank adaptation (LoRA) to pretrained NCAs, the authors show that simple rank‑one adjustments can control horizontal and vertical scaling of a 2D emoji phenotype, and that these adaptations generalize across diverse phenotypes sharing the same regulatory scaffold. Analysis of thousands of phenotype‑specific NCA adapters reveals latent low‑dimensional directions that govern scaling, style, and symmetrical fission, offering a computational realization of D’Arcy Thompson’s grid transformations in a minimal cybernetic tissue.

By Benedikt Hartl, Milton L. Montero, Marcello Barylli, Sebastian Risi, Michael Levin
fine-tuning
More like this →
arXiv AI
2d ago

Per-Node Activation Function Evolution in Indirectly Encoded Substrates: Solvability, Limits, and Emergent Diversity

The paper demonstrates that using a single activation function across all nodes in artificial neural networks imposes hard limits on evolutionary search, particularly for sparse evolved substrates. By evolving per-node activation functions from an 18-function palette, the authors show that oscillatory functions can solve parity problems at all tested scales, while monotonic functions fail beyond the simplest case. The study reveals that the choice of activation functions, beyond topology and weights, critically influences what evolutionary search can achieve, and that heterogeneous assignments discovered via indirect encoding are unlikely to be selected manually.

By Romain Claret, Michael O'Neill, Paul Cotofrei, Kilian Stoffel
efficiency
More like this →
arXiv AI
Jul 10

Architecture Generalization with MetaNCA

arXiv:2607. 07743v1 Announce Type: cross Abstract: Self-organization is an emergent property of life, driven by the collective behavior of individual components acting on local information.

By Meet Barot, Daniel Berenberg, Sina Khajehabdollahi
llms
More like this →