Reservoir computing with swarms

We study swarms as dynamical systems for reservoir computing (RC). By example of a modified Reynolds boids model, the specific symmetries and dynamical properties of a swarm are explored with respect to a nonlinear time-series prediction task. Specifically, we seek to extract meaningful information...

Full description

Bibliographic Details
Main Authors: Lymburn, T., Algar, S.D., Small, Michael, Jüngling, T.
Format: Journal Article
Language:English
Published: AIP Publishing 2021
Subjects:
Online Access:http://purl.org/au-research/grants/arc/IC180100030
http://hdl.handle.net/20.500.11937/91022
_version_ 1848765486182957056
author Lymburn, T.
Algar, S.D.
Small, Michael
Jüngling, T.
author_facet Lymburn, T.
Algar, S.D.
Small, Michael
Jüngling, T.
author_sort Lymburn, T.
building Curtin Institutional Repository
collection Online Access
description We study swarms as dynamical systems for reservoir computing (RC). By example of a modified Reynolds boids model, the specific symmetries and dynamical properties of a swarm are explored with respect to a nonlinear time-series prediction task. Specifically, we seek to extract meaningful information about a predator-like driving signal from the swarm's response to that signal. We find thatthe naïve implementation of a swarm for computation is very inefficient, as permutation symmetry of the individual agents reduces the computational capacity. To circumvent this, we distinguish between the computational substrate of the swarm and a separate observation layer, in which the swarm's response is measured for use in the task. We demonstrate the implementation of a radial basis-localized observation layer for this task. The behavior of the swarm is characterized by order parameters and measures of consistency and related to the performance of the swarm as a reservoir. The relationship between RC performance and swarm behavior demonstrates that optimal computational properties are obtained near a phase transition regime.
first_indexed 2025-11-14T11:36:01Z
format Journal Article
id curtin-20.500.11937-91022
institution Curtin University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T11:36:01Z
publishDate 2021
publisher AIP Publishing
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-910222023-05-17T06:37:38Z Reservoir computing with swarms Lymburn, T. Algar, S.D. Small, Michael Jüngling, T. Science & Technology Physical Sciences Mathematics, Applied Physics, Mathematical Mathematics Physics CONSISTENCY PROPERTIES DRIVEN COMPUTATION SYSTEM CHAOS We study swarms as dynamical systems for reservoir computing (RC). By example of a modified Reynolds boids model, the specific symmetries and dynamical properties of a swarm are explored with respect to a nonlinear time-series prediction task. Specifically, we seek to extract meaningful information about a predator-like driving signal from the swarm's response to that signal. We find thatthe naïve implementation of a swarm for computation is very inefficient, as permutation symmetry of the individual agents reduces the computational capacity. To circumvent this, we distinguish between the computational substrate of the swarm and a separate observation layer, in which the swarm's response is measured for use in the task. We demonstrate the implementation of a radial basis-localized observation layer for this task. The behavior of the swarm is characterized by order parameters and measures of consistency and related to the performance of the swarm as a reservoir. The relationship between RC performance and swarm behavior demonstrates that optimal computational properties are obtained near a phase transition regime. 2021 Journal Article http://hdl.handle.net/20.500.11937/91022 10.1063/5.0039745 English http://purl.org/au-research/grants/arc/IC180100030 AIP Publishing fulltext
spellingShingle Science & Technology
Physical Sciences
Mathematics, Applied
Physics, Mathematical
Mathematics
Physics
CONSISTENCY PROPERTIES
DRIVEN
COMPUTATION
SYSTEM
CHAOS
Lymburn, T.
Algar, S.D.
Small, Michael
Jüngling, T.
Reservoir computing with swarms
title Reservoir computing with swarms
title_full Reservoir computing with swarms
title_fullStr Reservoir computing with swarms
title_full_unstemmed Reservoir computing with swarms
title_short Reservoir computing with swarms
title_sort reservoir computing with swarms
topic Science & Technology
Physical Sciences
Mathematics, Applied
Physics, Mathematical
Mathematics
Physics
CONSISTENCY PROPERTIES
DRIVEN
COMPUTATION
SYSTEM
CHAOS
url http://purl.org/au-research/grants/arc/IC180100030
http://hdl.handle.net/20.500.11937/91022