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...
| Main Authors: | , , , |
|---|---|
| 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 |