Regression
Regression loss functions.
-
nabla.nn.losses.regression.mean_squared_error(predictions, targets)[source]
Compute mean squared error loss.
- Parameters:
predictions (Array) – Predicted values of shape (batch_size, …)
targets (Array) – Target values of shape (batch_size, …)
- Returns:
Scalar loss value
- Return type:
Array
-
nabla.nn.losses.regression.mean_absolute_error(predictions, targets)[source]
Compute mean absolute error loss.
- Parameters:
predictions (Array) – Predicted values of shape (batch_size, …)
targets (Array) – Target values of shape (batch_size, …)
- Returns:
Scalar loss value
- Return type:
Array
-
nabla.nn.losses.regression.huber_loss(predictions, targets, delta=1.0)[source]
Compute Huber loss (smooth L1 loss).
- Parameters:
predictions (Array) – Predicted values of shape (batch_size, …)
targets (Array) – Target values of shape (batch_size, …)
delta (float) – Threshold for switching between L1 and L2 loss
- Returns:
Scalar loss value
- Return type:
Array
