Unidirectional and Bidirectional LSTM Models for Short-Term Traffic Prediction

Table 1

Model hyperparameters for Uni-LSTM and BiLSTM.

Gradient decay factor	0.9
Initial learning rate	0.005
Minimum batch size	128
Maximum epochs	300
Training optimizer	Adaptive moment estimation optimizer
Dropping learning rate during training	Piecewise
Learning rate drop period	125
Factor for learning rate dropping	0.2