Click or drag to resize
Accord.NET (logo)

Accord.Math.Optimization.Losses Namespace

 
Classes
  ClassDescription
Public classAbsoluteLoss
Absolute loss, also known as L1-loss.
Public classBinaryCrossEntropyLoss
Binary cross-entropy loss for multi-label problems, also known as logistic loss per output of a multi-label classifier.
Public classCategoryCrossEntropyLoss
Categorical cross-entropy loss for multi-class problems, also known as the logistic loss for softmax (categorical) outputs.
Public classHammingLoss
Mean Accuracy loss, also known as zero-one-loss per class. Equivalent to ZeroOneLoss but for multi-label classifiers.
Public classLogLikelihoodLoss
Negative log-likelihood loss.
Public classLossBaseT
Base class for loss functions.
Public classLossBaseTInput, TScore, TLoss
Base class for loss functions.
Public classRSquaredLoss
R² (r-squared) loss.
Public classSquareLoss
Square loss, also known as L2-loss.
Public classZeroOneLoss
Accuracy loss, also known as zero-one-loss.
Structures
  StructureDescription
Public structureHingeLoss
Hinge loss.
Public structureLogisticLoss
Logistic loss.
Public structureSmoothHingeLoss
Smooth Hinge loss.
Public structureSquaredHingeLoss
Squared Hinge loss.
Interfaces