Table 5 Hyper-parameters of the network and their possible values

From: A stack LSTM structure for decoding continuous force from local field potential signal of primary motor cortex (M1)

Hyper-parameter Values
Layer 1 forward dropout {0, 0.1, 0.2, 0.3, 0.4, 0.5}
Layer 1 backward dropout {0, 0.1, 0.2, 0.3, 0.4, 0.5}
Layer 2 forward dropout {0, 0.1, 0.2, 0.3, 0.4, 0.5}
Layer 2 backward dropout {0, 0.1, 0.2, 0.3, 0.4, 0.5}
Regularization value {0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9}
Learning rate {0.001, 0.0015, 0.002, …, 0.003}
Batch size {5, 10, 15, 20,30}
Number of epoch {30, 50, 70, 100, 120}