Reservoir Computing with Evolved Critical Neural Cellular Automata

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pontes-Filho, Sidney, Nichele, Stefano, Lepperød, Mikkel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915443216744448
author Pontes-Filho, Sidney
Nichele, Stefano
Lepperød, Mikkel
author_facet Pontes-Filho, Sidney
Nichele, Stefano
Lepperød, Mikkel
contents Criticality is a behavioral state in dynamical systems that is known to present the highest computation capabilities, i.e., information transmission, storage, and modification. Therefore, such systems are ideal candidates as a substrate for reservoir computing, a subfield in artificial intelligence. Our choice of a substrate is a cellular automaton (CA) governed by an artificial neural network, also known as neural cellular automaton (NCA). We apply evolution strategy to optimize the NCA to achieve criticality, demonstrated by power law distributions in structures called avalanches. With an evolved critical NCA, the substrate is tested for reservoir computing. Our evaluation of the substrate is performed with two benchmarks, 5-bit memory task and image classification of handwritten digits. The result of the 5-bit memory task achieved a perfect score and the system managed to remember all 5 bits. The result for the image classification task matched and sometimes surpassed the performance of the best elementary CA for this task. Moreover, the proposed critical NCA may operate as a self-organized critical system, due to its robustness to extreme initial conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02218
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reservoir Computing with Evolved Critical Neural Cellular Automata
Pontes-Filho, Sidney
Nichele, Stefano
Lepperød, Mikkel
Neural and Evolutionary Computing
68T01
I.2.11
Criticality is a behavioral state in dynamical systems that is known to present the highest computation capabilities, i.e., information transmission, storage, and modification. Therefore, such systems are ideal candidates as a substrate for reservoir computing, a subfield in artificial intelligence. Our choice of a substrate is a cellular automaton (CA) governed by an artificial neural network, also known as neural cellular automaton (NCA). We apply evolution strategy to optimize the NCA to achieve criticality, demonstrated by power law distributions in structures called avalanches. With an evolved critical NCA, the substrate is tested for reservoir computing. Our evaluation of the substrate is performed with two benchmarks, 5-bit memory task and image classification of handwritten digits. The result of the 5-bit memory task achieved a perfect score and the system managed to remember all 5 bits. The result for the image classification task matched and sometimes surpassed the performance of the best elementary CA for this task. Moreover, the proposed critical NCA may operate as a self-organized critical system, due to its robustness to extreme initial conditions.
title Reservoir Computing with Evolved Critical Neural Cellular Automata
topic Neural and Evolutionary Computing
68T01
I.2.11
url https://arxiv.org/abs/2508.02218