Connecting reservoir computing with statistical forecasting and deep neural networks
Standfirst Among the existing machine learning frameworks, reservoir computing demonstrates fast and low-cost training, and its suitability for implementation in various physical systems. This Comment reports on how aspects of reservoir computing can be applied to classical forecasting methods to ac...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-01-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-021-27715-5 |
| _version_ | 1819008743943176192 |
|---|---|
| author | Lina Jaurigue Kathy Lüdge |
| author_facet | Lina Jaurigue Kathy Lüdge |
| author_sort | Lina Jaurigue |
| collection | DOAJ |
| description | Standfirst Among the existing machine learning frameworks, reservoir computing demonstrates fast and low-cost training, and its suitability for implementation in various physical systems. This Comment reports on how aspects of reservoir computing can be applied to classical forecasting methods to accelerate the learning process, and highlights a new approach that makes the hardware implementation of traditional machine learning algorithms practicable in electronic and photonic systems. |
| first_indexed | 2024-12-21T00:45:20Z |
| format | Article |
| id | doaj.art-fcc622d46d75426889c64c7a3621a113 |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-12-21T00:45:20Z |
| publishDate | 2022-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-fcc622d46d75426889c64c7a3621a1132022-12-21T19:21:33ZengNature PortfolioNature Communications2041-17232022-01-011311310.1038/s41467-021-27715-5Connecting reservoir computing with statistical forecasting and deep neural networksLina Jaurigue0Kathy Lüdge1Technische Universität Berlin, Institut für Theoretische PhysikTechnische Universität Ilmenau, Institut für PhysikStandfirst Among the existing machine learning frameworks, reservoir computing demonstrates fast and low-cost training, and its suitability for implementation in various physical systems. This Comment reports on how aspects of reservoir computing can be applied to classical forecasting methods to accelerate the learning process, and highlights a new approach that makes the hardware implementation of traditional machine learning algorithms practicable in electronic and photonic systems.https://doi.org/10.1038/s41467-021-27715-5 |
| spellingShingle | Lina Jaurigue Kathy Lüdge Connecting reservoir computing with statistical forecasting and deep neural networks Nature Communications |
| title | Connecting reservoir computing with statistical forecasting and deep neural networks |
| title_full | Connecting reservoir computing with statistical forecasting and deep neural networks |
| title_fullStr | Connecting reservoir computing with statistical forecasting and deep neural networks |
| title_full_unstemmed | Connecting reservoir computing with statistical forecasting and deep neural networks |
| title_short | Connecting reservoir computing with statistical forecasting and deep neural networks |
| title_sort | connecting reservoir computing with statistical forecasting and deep neural networks |
| url | https://doi.org/10.1038/s41467-021-27715-5 |
| work_keys_str_mv | AT linajaurigue connectingreservoircomputingwithstatisticalforecastinganddeepneuralnetworks AT kathyludge connectingreservoircomputingwithstatisticalforecastinganddeepneuralnetworks |