pihnn.utils.km_loss

pihnn.utils.km_loss(boundary, model, t)

Called by pihnn.utils.PIHNNloss() if one aims to solve the linear elasticity problem through the Kolosov-Muskhelishvili representation.

Parameters:

• boundary (pihnn.geometries.boundary) – Domain boundary, needed to extract training and test points.

• model (pihnn.nn.PIHNN/pihnn.nn.DD_PIHNN) – Neural network model.

• t (str) – Option for ‘training’ or ‘test’.

Returns:

loss (float) - Computed loss.