Table 10 Hyperparameter set-up for the best found ELM models for each regression dataset
From: Extreme learning machine versus classical feedforward network
Dataset | Hidden layer size | Activation function | Regularisation coefficient |
|---|---|---|---|
Servo | 10 | Tanh | 10 |
Machine CPU | 10,000 | Tanh | 0.1 |
Auto MPG | 100 | Tanh | 0.003 |
Delta ailerons | 10 | ReLU | 0.001 |
Bank | 10 | ReLU | 0.001 |
California housing | 300 | ReLU | 10 |