An introduction to delay-coupled reservoir computing
Autor(en): | Schumacher, J. Toutounji, H. Pipa, G. |
Stichwörter: | Differential equations; Neural networks, Analytical approximation; Approximate analytical; Computational costs; Delay differential equations; Nonlinear computations; Reservoir Computing; Theoretical investigations; Time series prediction, Benchmarking | Erscheinungsdatum: | 2015 | Herausgeber: | Springer Verlag | Journal: | Artificial Neural Networks - Methods and Applications in Bio-/Neuroinformatics | Startseite: | 63 | Seitenende: | 90 | Zusammenfassung: | Reservoir computing has been successfully applied in difficult time series prediction tasks by injecting an input signal into a spatially extended reservoir of nonlinear subunits to perform history-dependent nonlinear computation. Recently, the network was replaced by a single nonlinear node, delay-coupled to itself. Instead of a spatial topology, subunits are arrayed in time along one delay span of the system. As a result, the reservoir exists only implicitly in a single delay differential equation, the numerical solving of which is costly. We give here a brief introduction to the general topic of delay-coupled reservoir computing and derive approximate analytical equations for the reservoir by solving the underlying system explicitly. The analytical approximation represents the system accurately and yields comparable performance in reservoir benchmark tasks, while reducing computational costs practically by several orders of magnitude. This has important implications with respect to electronic realizations of the reservoir and opens up new possibilities for optimization and theoretical investigation. © Springer International Publishing Switzerland 2015. |
Beschreibung: | Conference of 23rd International Conference on Artificial Neural Networks, ICANN 2013 ; Conference Date: 10 September 2013 Through 13 September 2013; Conference Code:176539 |
ISBN: | 9783319099026 | DOI: | 10.1007/978-3-319-09903-3_4 | Externe URL: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85008391932&doi=10.1007%2f978-3-319-09903-3_4&partnerID=40&md5=305d373bb5d8f72cced09dcdfd61dc92 |
Zur Langanzeige
Seitenaufrufe
3
Letzte Woche
0
0
Letzter Monat
0
0
geprüft am 02.05.2024