Reservoir computing with swarms
Citation
Source Title
ISSN
Faculty
School
Funding and Sponsorship
Remarks
Reproduced from Chaos 31, 033121 (2021), with the permission of AIP Publishing
Collection
Abstract
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.
Related items
Showing items related by title, author, creator and subject.
-
Ortega-Sanchez, Cesar; Hamer, M. (2010)One major problem in the development of robotic swarms is the slow process of testing. Testing different algorithms or variations of a single one using physical robots requires reprogramming every robot in the swarm before ...
-
Jourdan, Fred; Feraud, G.; Bertrand, H.; Watkeys, M.; Kampunzu, A.; LeGall, B. (2006)Continental flood basalts consist of vast quantities of lava, sills and giant dyke swarms that are associated with continental break-up. The commonly radiating geometry of dyke swarms in these provinces is generally ...
-
LeGall, B.; Tshoso, G.; Dyment, J.; Kampunzu, A.; Jourdan, Fred; Feraud, G.; Bertrand, H.; Aubourg, C.; Vétel, William (2005)The structural organization of a giant mafic dyke swarm, the Okavango complex, in the northern Karoo Large Igneous Province (LIP) of NE Botswana is detailed. This N110E-oriented dyke swarm extends for 1500 km with a maximum ...