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

Köster, Felix; Yanchuk, Serhiy; Lüdge, Kathy

doi:10.1109/TNNLS.2022.3220532

アイテム詳細

登録内容を編集ファイル形式で保存

一時保存へ追加

タグ情報を表示リリース履歴を表示詳細要約

公開

学術論文

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

Authors

Köster, Felix
External Organizations;

/persons/resource/yanchuk

Yanchuk, Serhiy
Potsdam Institute for Climate Impact Research;

Lüdge, Kathy
External Organizations;

URL

There are no locators available

フルテキスト (公開)

27572oa.pdf
(出版社版), 2MB

付随資料 (公開)

There is no public supplementary material available

引用

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. doi:10.1109/TNNLS.2022.3220532.

引用: https://publications.pik-potsdam.de/pubman/item/item_27572

要旨

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.