Table 2 Hyperparameters for DEEPLYESSENTIAL
From: DeeplyEssential: a deep neural network for predicting essential genes in microbes
Parameters | Range | Selected parameter |
|---|---|---|
# hidden layers | [2 - 8] | 6 |
# nodes | [32, 64, 128, 512, 1024, 2048] | 128, 256, 512, 1024, 1024, 1024 |
Dropout rate | [0.1 - 0.5] | 0.3 |
Epochs | – | 100 (early stopping) |
Optimizer | sgd, adam, adadelta, RMSProp | adadelta |