Ma, Haochun und Prosperino, Davide und Haluszczynski, Alexander und Räth, Christoph (2023) Efficient forecasting of chaotic systems with block-diagonal and binary reservoir computing. Chaos. American Institute of Physics (AIP). doi: 10.1063/5.0151290. ISSN 1054-1500.
PDF
- Verlagsversion (veröffentlichte Fassung)
2MB |
Offizielle URL: https://doi.org/10.1063/5.0151290
Kurzfassung
The prediction of complex nonlinear dynamical systems with the help of machine learning has become increasingly popular in different areas of science. In particular, reservoir computers, also known as echo-state networks, turned out to be a very powerful approach, especially for the reproduction of nonlinear systems. The reservoir, the key component of this method, is usually constructed as a sparse, random network that serves as a memory for the system. In this work, we introduce block-diagonal reservoirs, which implies that a reservoir can be composed of multiple smaller reservoirs, each with its own dynamics. Furthermore, we take out the randomness of the reservoir by using matrices of ones for the individual blocks. This breaks with the widespread interpretation of the reservoir as a single network. In the example of the Lorenz and Halvorsen systems, we analyze the performance of block-diagonal reservoirs and their sensitivity to hyperparameters. We find that the performance is comparable to sparse random networks and discuss the implications with regard to scalability, explainability, and hardware realizations of reservoir computers.
elib-URL des Eintrags: | https://elib.dlr.de/195466/ | ||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Zeitschriftenbeitrag | ||||||||||||||||||||
Titel: | Efficient forecasting of chaotic systems with block-diagonal and binary reservoir computing | ||||||||||||||||||||
Autoren: |
| ||||||||||||||||||||
Datum: | 12 Juni 2023 | ||||||||||||||||||||
Erschienen in: | Chaos | ||||||||||||||||||||
Referierte Publikation: | Ja | ||||||||||||||||||||
Open Access: | Ja | ||||||||||||||||||||
Gold Open Access: | Nein | ||||||||||||||||||||
In SCOPUS: | Ja | ||||||||||||||||||||
In ISI Web of Science: | Ja | ||||||||||||||||||||
DOI: | 10.1063/5.0151290 | ||||||||||||||||||||
Verlag: | American Institute of Physics (AIP) | ||||||||||||||||||||
ISSN: | 1054-1500 | ||||||||||||||||||||
Status: | veröffentlicht | ||||||||||||||||||||
Stichwörter: | Complex Systems, AI, Reservoir Computing, Prediction, Time Series Analysis | ||||||||||||||||||||
HGF - Forschungsbereich: | keine Zuordnung | ||||||||||||||||||||
HGF - Programm: | keine Zuordnung | ||||||||||||||||||||
HGF - Programmthema: | keine Zuordnung | ||||||||||||||||||||
DLR - Schwerpunkt: | Digitalisierung | ||||||||||||||||||||
DLR - Forschungsgebiet: | D KIZ - Künstliche Intelligenz | ||||||||||||||||||||
DLR - Teilgebiet (Projekt, Vorhaben): | D - PISA | ||||||||||||||||||||
Standort: | Oberpfaffenhofen | ||||||||||||||||||||
Institute & Einrichtungen: | Institut für KI-Sicherheit | ||||||||||||||||||||
Hinterlegt von: | Räth, Christoph | ||||||||||||||||||||
Hinterlegt am: | 15 Jun 2023 12:37 | ||||||||||||||||||||
Letzte Änderung: | 13 Jun 2024 03:00 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags