Show / Hide Table of Contents

Class MeanSquaredLogError

Mean squared logarithmic error (MSLE) is, as the name suggests, a variation of the Mean Squared Error. The loss is the mean over the seen data of the squared differences between the log-transformed true and predicted values, or writing it as a formula: where ŷ is the predicted value.

Inheritance
System.Object
BaseLoss
MeanSquaredLogError
Inherited Members
BaseLoss.Name
Namespace: SiaNet.Losses
Assembly: SiaNet.dll
Syntax
public class MeanSquaredLogError : BaseLoss

Constructors

| Improve this Doc View Source

MeanSquaredLogError()

Initializes a new instance of the MeanSquaredLogError class.

Declaration
public MeanSquaredLogError()

Methods

| Improve this Doc View Source

Backward(Tensor, Tensor)

Backpropagation method to calculate gradient of the loss function

Declaration
public override Tensor Backward(Tensor preds, Tensor labels)
Parameters
Type Name Description
Tensor preds

The predicted result.

Tensor labels

The true result.

Returns
Type Description
Tensor
Overrides
BaseLoss.Backward(Tensor, Tensor)
| Improve this Doc View Source

Forward(Tensor, Tensor)

Forwards the inputs and calculate the loss.

Declaration
public override Tensor Forward(Tensor preds, Tensor labels)
Parameters
Type Name Description
Tensor preds

The predicted result.

Tensor labels

The true result.

Returns
Type Description
Tensor
Overrides
BaseLoss.Forward(Tensor, Tensor)

See Also

BaseLoss
  • Improve this Doc
  • View Source
Back to top Generated by DocFX