TABLE XI.
Optimal Hyperparameters for MGH NeuroBank Corpus Level 5
| GCNN | regularization | 5.00e–2 |
| decay_steps | 400 | |
| learning_rate | 1.00e–3 | |
| pool | apool1 | |
| momentum | 9.00e–1 | |
| num_epochs | 350 | |
| batch_size | 20 | |
| M | [100, 60] | |
| ps | [[2]] | |
| decay_rate | 9.60e–1 | |
| Ks | [[7]] | |
| Fs | [[25]] | |
| dropout | 5.00e–1 | |
| FF-ANN | hidden_layer_sizes | [946, 193] |
| alpha | 1.11 | |
| power_t | 8.87e–1 | |
| early_stopping | False | |
| learning_rate_init | 9.86e–1 | |
| nesterovs_momentum | True | |
| learning_rate | constant | |
| momentum | 8.76e–1 | |
| activation | relu | |
| KNNs | n_neighbors | 7 |
| metric | canberra | |
| weights | distance | |
| Linear Classifier | learning_rate | invscaling |
| tol | 1.00e–5 | |
| n_jobs | −1 | |
| power_t | 1.84e–1 | |
| penalty | l1 | |
| eta0 | 3.17e–4 | |
| loss | log | |
| l1_ratio | 4.06e–1 | |
| alpha | 1.23e–3 | |
| Random Forest | max_depth | 25 |
| max_leaf_nodes | 500 | |
| min_weight_fraction_leaf | 4.33e–4 | |
| min_samples_split | 2 | |
| min_samples_leaf | 1 | |
| n_estimators | 411 | |
| criterion | gini | |
| min_impurity_decrease | 3.64e–5 | |
| Decision Tree | min_samples_split | 2 |
| max_depth | 10 | |
| criterion | entropy | |
| min_impurity_decrease | 1.23e–3 | |
| max_leaf_nodes | None | |
| min_weight_fraction_leaf | 2.08e–3 | |
| min_samples_leaf | 2 | |
| max_features | None | |
| splitter | best |