Deutsch
 
Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT

Freigegeben

Zeitschriftenartikel

Master Memory Function for Delay-Based Reservoir Computers With Single-Variable Dynamics

Urheber*innen

Köster,  Felix
External Organizations;

/persons/resource/yanchuk

Yanchuk,  Serhiy
Potsdam Institute for Climate Impact Research;

Lüdge,  Kathy
External Organizations;

Externe Ressourcen
Es sind keine externen Ressourcen hinterlegt
Volltexte (frei zugänglich)

27572oa.pdf
(Verlagsversion), 2MB

Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Köster, F., Yanchuk, S., Lüdge, K. (2024): Master Memory Function for Delay-Based Reservoir Computers With Single-Variable Dynamics. - IEEE Transactions on Neural Networks and Learning Systems, 35, 6, 7712-7725.
https://doi.org/10.1109/TNNLS.2022.3220532


Zitierlink: https://publications.pik-potsdam.de/pubman/item/item_27572
Zusammenfassung
We show that many delay-based reservoir computers considered in the literature can be characterized by a universal master memory function (MMF). Once computed for two independent parameters, this function provides linear memory capacity for any delay-based single-variable reservoir with small inputs. Moreover, we propose an analytical description of the MMF that enables its efficient and fast computation. Our approach can be applied not only to single-variable delay-based reservoirs governed by known dynamical rules, such as the Mackey–Glass or Stuart–Landau-like systems, but also to reservoirs whose dynamical model is not available.