Table 2 The list of LSTM hyperparameters and the final values obtained from the grid search.
Hyper parameter | Description | Value |
|---|---|---|
Number of steps | Number of observations in a single sequence of input data | 100 |
Number of features | Number of input variables used to train the LSTM model | 2 |
Max epochs | Maximum number of times the model iterates over the training dataset | 1 |
Batch size | Number of samples processed by the model in each training iteration | 4 |
Optimizer | Optimization algorithm used to minimize the loss function during training | Adam |
Layers | The number of LSTM units stacked on top of each other | 3 layers (4, 4, 1) |
Activation function | Element-wise nonlinear function applied to the output of each LSTM unit | Tanh, sigmoid |
