Reservoir Computing with Delayed Input for Fast and Easy Optimisation
Reservoir computing is a machine learning method that solves tasks using the response of a dynamical system to a certain input. As the training scheme only involves optimising the weights of the responses of the dynamical system, this method is particularly suited for hardware implementation. Furthe...
Main Authors: | Lina Jaurigue, Elizabeth Robertson, Janik Wolters, Kathy Lüdge |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/23/12/1560 |
Similar Items
-
Reducing reservoir computer hyperparameter dependence by external timescale tailoring
by: Lina Jaurigue, et al.
Published: (2024-01-01) -
Efficient optimisation of physical reservoir computers using only a delayed input
by: Enrico Picco, et al.
Published: (2025-01-01) -
Post-processing methods for delay embedding and feature scaling of reservoir computers
by: Jonnel Jaurigue, et al.
Published: (2025-01-01) -
Deriving task specific performance from the information processing capacity of a reservoir computer
by: Hülser Tobias, et al.
Published: (2022-10-01) -
Connecting reservoir computing with statistical forecasting and deep neural networks
by: Lina Jaurigue, et al.
Published: (2022-01-01)