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
Description
Summary: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.