Learning from the past: reservoir computing using delayed variables
Reservoir computing is a machine learning method that is closely linked to dynamical systems theory. This connection is highlighted in a brief introduction to the general concept of reservoir computing. We then address a recently suggested approach to improve the performance of reservoir systems by...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-03-01
|
| Series: | Frontiers in Applied Mathematics and Statistics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fams.2024.1221051/full |
| _version_ | 1797289721101025280 |
|---|---|
| author | Ulrich Parlitz Ulrich Parlitz |
| author_facet | Ulrich Parlitz Ulrich Parlitz |
| author_sort | Ulrich Parlitz |
| collection | DOAJ |
| description | Reservoir computing is a machine learning method that is closely linked to dynamical systems theory. This connection is highlighted in a brief introduction to the general concept of reservoir computing. We then address a recently suggested approach to improve the performance of reservoir systems by incorporating past values of the input signal or of the reservoir state variables into the readout used to forecast the input or cross-predict other variables of interest. The efficiency of this extension is illustrated by a minimal example in which a three-dimensional reservoir system based on the Lorenz-63 model is used to predict the variables of a chaotic Rössler system. |
| first_indexed | 2024-03-07T19:10:05Z |
| format | Article |
| id | doaj.art-22ee4c10a6754602b21ef3f87232f84d |
| institution | Directory Open Access Journal |
| issn | 2297-4687 |
| language | English |
| last_indexed | 2024-03-07T19:10:05Z |
| publishDate | 2024-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Applied Mathematics and Statistics |
| spelling | doaj.art-22ee4c10a6754602b21ef3f87232f84d2024-03-01T04:56:47ZengFrontiers Media S.A.Frontiers in Applied Mathematics and Statistics2297-46872024-03-011010.3389/fams.2024.12210511221051Learning from the past: reservoir computing using delayed variablesUlrich Parlitz0Ulrich Parlitz1Biomedical Physics Group, Max Planck Institute for Dynamics and Self-Organization, Göttingen, GermanyInstitute for the Dynamics of Complex Systems, Georg-August-Universität Göttingen, Göttingen, GermanyReservoir computing is a machine learning method that is closely linked to dynamical systems theory. This connection is highlighted in a brief introduction to the general concept of reservoir computing. We then address a recently suggested approach to improve the performance of reservoir systems by incorporating past values of the input signal or of the reservoir state variables into the readout used to forecast the input or cross-predict other variables of interest. The efficiency of this extension is illustrated by a minimal example in which a three-dimensional reservoir system based on the Lorenz-63 model is used to predict the variables of a chaotic Rössler system.https://www.frontiersin.org/articles/10.3389/fams.2024.1221051/fullecho state networksecho state propertygeneralized synchronizationchaotic time series predictionnon-linear observerdelay embedding |
| spellingShingle | Ulrich Parlitz Ulrich Parlitz Learning from the past: reservoir computing using delayed variables Frontiers in Applied Mathematics and Statistics echo state networks echo state property generalized synchronization chaotic time series prediction non-linear observer delay embedding |
| title | Learning from the past: reservoir computing using delayed variables |
| title_full | Learning from the past: reservoir computing using delayed variables |
| title_fullStr | Learning from the past: reservoir computing using delayed variables |
| title_full_unstemmed | Learning from the past: reservoir computing using delayed variables |
| title_short | Learning from the past: reservoir computing using delayed variables |
| title_sort | learning from the past reservoir computing using delayed variables |
| topic | echo state networks echo state property generalized synchronization chaotic time series prediction non-linear observer delay embedding |
| url | https://www.frontiersin.org/articles/10.3389/fams.2024.1221051/full |
| work_keys_str_mv | AT ulrichparlitz learningfromthepastreservoircomputingusingdelayedvariables AT ulrichparlitz learningfromthepastreservoircomputingusingdelayedvariables |