Table 3 Burgers’ problem: hyperparameters for the LSTM network

Sequence length (\(n_t\))

5, 10, 20

LSTM layers

1, 2, 3

hidden/latent dimension (m)

12,25,50

Activation

tanh

Loss function

MSE

Learning rate

\(5 \times 10^{-4}\)

Max model parameters (\(n_t = 10\))

20,400

Min model parameters (\(n_t = 10\))

1248