Next generation reservoir computing
Reservoir computers are artificial neural networks that can be trained on small data sets, but require large random matrices and numerous metaparameters. The authors propose an improved reservoir computer that overcomes these limitations and shows advantageous performance for complex forecasting tas...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Publishing Group
2021-09-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-021-25801-2 |
| id |
doaj-a188e94135aa40e8af0b78655f0dc46a |
|---|---|
| record_format |
Article |
| spelling |
doaj-a188e94135aa40e8af0b78655f0dc46a2021-09-26T11:45:11ZengNature Publishing GroupNature Communications2041-17232021-09-011211810.1038/s41467-021-25801-2Next generation reservoir computingDaniel J. Gauthier0Erik Bollt1Aaron Griffith2Wendson A. S. Barbosa3The Ohio State University, Department of PhysicsClarkson University, Department of Electrical and Computer EngineeringThe Ohio State University, Department of PhysicsThe Ohio State University, Department of PhysicsReservoir computers are artificial neural networks that can be trained on small data sets, but require large random matrices and numerous metaparameters. The authors propose an improved reservoir computer that overcomes these limitations and shows advantageous performance for complex forecasting taskshttps://doi.org/10.1038/s41467-021-25801-2 |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Daniel J. Gauthier Erik Bollt Aaron Griffith Wendson A. S. Barbosa |
| spellingShingle |
Daniel J. Gauthier Erik Bollt Aaron Griffith Wendson A. S. Barbosa Next generation reservoir computing Nature Communications |
| author_facet |
Daniel J. Gauthier Erik Bollt Aaron Griffith Wendson A. S. Barbosa |
| author_sort |
Daniel J. Gauthier |
| title |
Next generation reservoir computing |
| title_short |
Next generation reservoir computing |
| title_full |
Next generation reservoir computing |
| title_fullStr |
Next generation reservoir computing |
| title_full_unstemmed |
Next generation reservoir computing |
| title_sort |
next generation reservoir computing |
| publisher |
Nature Publishing Group |
| series |
Nature Communications |
| issn |
2041-1723 |
| publishDate |
2021-09-01 |
| description |
Reservoir computers are artificial neural networks that can be trained on small data sets, but require large random matrices and numerous metaparameters. The authors propose an improved reservoir computer that overcomes these limitations and shows advantageous performance for complex forecasting tasks |
| url |
https://doi.org/10.1038/s41467-021-25801-2 |
| work_keys_str_mv |
AT danieljgauthier nextgenerationreservoircomputing AT erikbollt nextgenerationreservoircomputing AT aarongriffith nextgenerationreservoircomputing AT wendsonasbarbosa nextgenerationreservoircomputing |
| _version_ |
1716867793770512384 |