Research Article
Broad Echo State Network with Reservoir Pruning for Nonstationary Time Series Prediction
Table 2
Network model parameters of Fangshan District air quality dataset in Beijing.
| | Hyperparameter | BPESN | BESN | ESN | BLS |
| | Number of neurons in mapping layer | 1–15 | 1–15 | N/A | 1–15 | | Number of neurons in enhancement layer | 1–20 | 1–20 | N/A | 1–20 | | Reservoir size | 400–800 | 400–800 | 400–800 | N/A | | Spectral radius rate | 0.95 | 0.95 | 0.95 | N/A | | Leaking rate | 0.1 | 0.1 | 0.1 | N/A | | Sparseness | 0.05 | 0.05 | 0.05 | N/A | | Pruning the number of times | 1–10 | N/A | N/A | N/A |
|
|