Saved in:
Bibliographic Details
Main Authors: Barandiaran, Matias, Stovold, James
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.08091
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908704124698624
author Barandiaran, Matias
Stovold, James
author_facet Barandiaran, Matias
Stovold, James
contents Developmental Graph Cellular Automata (DGCA) are a novel model for morphogenesis, capable of growing directed graphs from single-node seeds. In this paper, we show that DGCAs can be trained to grow reservoirs. Reservoirs are grown with two types of targets: task-driven (using the NARMA family of tasks) and task-independent (using reservoir metrics). Results show that DGCAs are able to grow into a variety of specialized, life-like structures capable of effectively solving benchmark tasks, statistically outperforming `typical' reservoirs on the same task. Overall, these lay the foundation for the development of DGCA systems that produce plastic reservoirs and for modeling functional, adaptive morphogenesis.
format Preprint
id arxiv_https___arxiv_org_abs_2508_08091
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Growing Reservoirs with Developmental Graph Cellular Automata
Barandiaran, Matias
Stovold, James
Neural and Evolutionary Computing
Artificial Intelligence
Developmental Graph Cellular Automata (DGCA) are a novel model for morphogenesis, capable of growing directed graphs from single-node seeds. In this paper, we show that DGCAs can be trained to grow reservoirs. Reservoirs are grown with two types of targets: task-driven (using the NARMA family of tasks) and task-independent (using reservoir metrics). Results show that DGCAs are able to grow into a variety of specialized, life-like structures capable of effectively solving benchmark tasks, statistically outperforming `typical' reservoirs on the same task. Overall, these lay the foundation for the development of DGCA systems that produce plastic reservoirs and for modeling functional, adaptive morphogenesis.
title Growing Reservoirs with Developmental Graph Cellular Automata
topic Neural and Evolutionary Computing
Artificial Intelligence
url https://arxiv.org/abs/2508.08091