Table 7 Hyperparameters for the LSTM layer
From: An alternative approach to dimension reduction for pareto distributed data: a case study
Hyperparameter | Value |
|---|---|
Activation function | “tanh” |
Recurrent activation | “Sigmoid” |
Use bias | True |
Kernel initializer | “Glorot uniform” |
Recurrent initializer | “orthogonal” |
Bias initializer | “zeros” |