Composite FORCE learning of chaotic echo state networks for time-series prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914645463269376 |
|---|---|
| author | Li, Yansong Hu, Kai Nakajima, Kohei Pan, Yongping |
| author_facet | Li, Yansong Hu, Kai Nakajima, Kohei Pan, Yongping |
| contents | Echo state network (ESN), a kind of recurrent neural networks, consists of a fixed reservoir in which neurons are connected randomly and recursively and obtains the desired output only by training output connection weights. First-order reduced and controlled error (FORCE) learning is an online supervised training approach that can change the chaotic activity of ESNs into specified activity patterns. This paper proposes a composite FORCE learning method based on recursive least squares to train ESNs whose initial activity is spontaneously chaotic, where a composite learning technique featured by dynamic regressor extension and memory data exploitation is applied to enhance parameter convergence. The proposed method is applied to a benchmark problem about predicting chaotic time series generated by the Mackey-Glass system, and numerical results have shown that it significantly improves learning and prediction performances compared with existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2207_02420 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Composite FORCE learning of chaotic echo state networks for time-series prediction Li, Yansong Hu, Kai Nakajima, Kohei Pan, Yongping Machine Learning Neural and Evolutionary Computing Echo state network (ESN), a kind of recurrent neural networks, consists of a fixed reservoir in which neurons are connected randomly and recursively and obtains the desired output only by training output connection weights. First-order reduced and controlled error (FORCE) learning is an online supervised training approach that can change the chaotic activity of ESNs into specified activity patterns. This paper proposes a composite FORCE learning method based on recursive least squares to train ESNs whose initial activity is spontaneously chaotic, where a composite learning technique featured by dynamic regressor extension and memory data exploitation is applied to enhance parameter convergence. The proposed method is applied to a benchmark problem about predicting chaotic time series generated by the Mackey-Glass system, and numerical results have shown that it significantly improves learning and prediction performances compared with existing methods. |
| title | Composite FORCE learning of chaotic echo state networks for time-series prediction |
| topic | Machine Learning Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2207.02420 |