Table 14 Hyperparameter set-up for the best found ELM models for each classification dataset
From: Extreme learning machine versus classical feedforward network
Dataset | Number of kernels | Kernel size | Pooling size | Regularisation coefficient |
|---|---|---|---|---|
CIFAR-10 | 64 | 3 | 5 | 10 |
MNIST | 64 | 5 | 7 | 10 |
NORB | 48 | 3 | 3 | 3 |
GTSRB | 64 | 7 | 3 | 3 |
ImageNet16 | 48 | 3 | 3 | 3 |
ImageNet32 | 8 | 3 | 3 | 1 |