Cargando…

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Jaurigue, Lina, Robertson, Elizabeth, Wolters, Janik, Lüdge, Kathy
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8700644/
https://www.ncbi.nlm.nih.gov/pubmed/34945866
http://dx.doi.org/10.3390/e23121560
_version_ 1784620806900285440
author Jaurigue, Lina
Robertson, Elizabeth
Wolters, Janik
Lüdge, Kathy
author_facet Jaurigue, Lina
Robertson, Elizabeth
Wolters, Janik
Lüdge, Kathy
author_sort Jaurigue, Lina
collection PubMed
description 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. Furthermore, the inherent memory of dynamical systems which are suitable for use as reservoirs mean that this method has the potential to perform well on time series prediction tasks, as well as other tasks with time dependence. However, reservoir computing still requires extensive task-dependent parameter optimisation in order to achieve good performance. We demonstrate that by including a time-delayed version of the input for various time series prediction tasks, good performance can be achieved with an unoptimised reservoir. Furthermore, we show that by including the appropriate time-delayed input, one unaltered reservoir can perform well on six different time series prediction tasks at a very low computational expense. Our approach is of particular relevance to hardware implemented reservoirs, as one does not necessarily have access to pertinent optimisation parameters in physical systems but the inclusion of an additional input is generally possible.
format Online
Article
Text
id pubmed-8700644
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-87006442021-12-24 Reservoir Computing with Delayed Input for Fast and Easy Optimisation Jaurigue, Lina Robertson, Elizabeth Wolters, Janik Lüdge, Kathy Entropy (Basel) Article 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. Furthermore, the inherent memory of dynamical systems which are suitable for use as reservoirs mean that this method has the potential to perform well on time series prediction tasks, as well as other tasks with time dependence. However, reservoir computing still requires extensive task-dependent parameter optimisation in order to achieve good performance. We demonstrate that by including a time-delayed version of the input for various time series prediction tasks, good performance can be achieved with an unoptimised reservoir. Furthermore, we show that by including the appropriate time-delayed input, one unaltered reservoir can perform well on six different time series prediction tasks at a very low computational expense. Our approach is of particular relevance to hardware implemented reservoirs, as one does not necessarily have access to pertinent optimisation parameters in physical systems but the inclusion of an additional input is generally possible. MDPI 2021-11-23 /pmc/articles/PMC8700644/ /pubmed/34945866 http://dx.doi.org/10.3390/e23121560 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Jaurigue, Lina
Robertson, Elizabeth
Wolters, Janik
Lüdge, Kathy
Reservoir Computing with Delayed Input for Fast and Easy Optimisation
title Reservoir Computing with Delayed Input for Fast and Easy Optimisation
title_full Reservoir Computing with Delayed Input for Fast and Easy Optimisation
title_fullStr Reservoir Computing with Delayed Input for Fast and Easy Optimisation
title_full_unstemmed Reservoir Computing with Delayed Input for Fast and Easy Optimisation
title_short Reservoir Computing with Delayed Input for Fast and Easy Optimisation
title_sort reservoir computing with delayed input for fast and easy optimisation
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8700644/
https://www.ncbi.nlm.nih.gov/pubmed/34945866
http://dx.doi.org/10.3390/e23121560
work_keys_str_mv AT jauriguelina reservoircomputingwithdelayedinputforfastandeasyoptimisation
AT robertsonelizabeth reservoircomputingwithdelayedinputforfastandeasyoptimisation
AT woltersjanik reservoircomputingwithdelayedinputforfastandeasyoptimisation
AT ludgekathy reservoircomputingwithdelayedinputforfastandeasyoptimisation