mlx.nn.losses.mse_loss#

mse_loss(predictions: array, targets: array, reduction: Literal['none', 'mean', 'sum'] = 'mean') array#

Computes the mean squared error loss.

Parameters:
  • predictions (array) – The predicted values.

  • targets (array) – The target values.

  • reduction (str, optional) – Specifies the reduction to apply to the output: 'none' | 'mean' | 'sum'. Default: 'mean'.

Returns:

The computed mean squared error loss.

Return type:

array