Table 4 The hyperparameters of TPE optimized LightGBM model.
From: A novel stroke classification model based on EEG feature fusion
Hyperparameters name | Value |
|---|---|
n_estimators | 15,000 |
learning_rate | 0.15019970599177168 |
num_leaves | 2555 |
max_depth | 6 |
min_data_in_leaf | 200 |
max_bin | 291 |
lambda_l1 | 2 |
lambda_l2 | 58 |
min_gain_to_split | 0.0018095911494751889 |
bagging_fraction | 0.95 |
bagging_freq | 1 |
feature_fraction | 0.30000000000000004 |
