PirateNet Block

class PirateNetBlock(inner_size, activation)

Bases: Module

The inner block of Physics-Informed residual adaptive network (PirateNet).

The block consists of three dense layers with dual gating operations and an adaptive residual connection. The trainable alpha parameter controls the contribution of the residual connection.

See also

Original reference: Wang, S., Sankaran, S., Stinis., P., Perdikaris, P. (2025). Simulating Three-dimensional Turbulence with Physics-informed Neural Networks. DOI: arXiv preprint arXiv:2507.08972.

Initialization of the PirateNetBlock class.

Parameters:

• inner_size (int) – The number of hidden units in the dense layers.

• activation (torch.nn.Module) – The activation function.

forward(x, U, V)

Forward pass of the PirateNet block. It computes the output of the block by applying the dense layers with scaling, and combines the results with the input using the adaptive residual connection.

Parameters:

• x (torch.Tensor | LabelTensor) – The input tensor.

• U (torch.Tensor) – The first shared gating tensor. It must have the same shape as x.

• V (torch.Tensor) – The second shared gating tensor. It must have the same shape as x.

Returns:

The output tensor of the block.

Return type:

torch.Tensor | LabelTensor

property alpha

Return the alpha parameter.

Returns:

The alpha parameter controlling the residual connection.

Return type:

torch.nn.Parameter