Deterministic reservoir computing for chaotic time series prediction
Abstract Reservoir Computing was shown in recent years to be useful as efficient to learn networks in the field of time series tasks. Their randomized initialization, a computational benefit, results in drawbacks in theoretical analysis of large random graphs, because of which deterministic variatio...
Saved in:
| Main Authors: | Johannes Viehweg, Constanze Poll, Patrick Mäder |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-98172-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Enhanced predictive capability for chaotic dynamics by modified quantum reservoir computing
by: Longhan Wang, et al.
Published: (2024-11-01) -
Chaotic proliferation of relativistic domain walls for reservoir computing
by: J. A. Vélez, et al.
Published: (2025-04-01) -
The <i>Drosophila</i> Connectome as a Computational Reservoir for Time-Series Prediction
by: Leone Costi, et al.
Published: (2025-05-01) -
Deterministic Discrete Dynamical Systems: Advances in Regular and Chaotic Behavior with Applications
by: Raghib Abu-Saris, et al.
Published: (2013-01-01) -
Prediction for Chaotic Time Series-Based AE-CNN and Transfer Learning
by: Baogui Xin, et al.
Published: (2020-01-01)