Table 5 Deep learning optimizers' hyperparameter specification
From: Early prediction of chronic kidney disease based on ensemble of deep learning models and optimizers
Optimizer | Specification |
|---|---|
Adamax | Learning rate = 0.0009, beta1 = 0.9, beta2 = 0.99, epsilon = 1 × 10−8 |
Adam | Learning rate = 0.0009, beta1 = 0.9, beta2 = 0.99, epsilon = 1 × 10−8 |
SGD | Learning rate = 0.0009, momentum = 0.9, nesterov = False |
Adadelta | Learning rate = 0.0009, rho = 0.95, epsilon = 1 × 10−6 |
Adagrad | Learning rate = 0.0009, epsilon = 1 × 10−7 |