Accord.Math.Optimization.Losses Namespace 
Class  Description  

AbsoluteLoss 
Absolute loss, also known as L1loss.
 
BinaryCrossEntropyLoss 
Binary crossentropy loss for multilabel problems, also
known as logistic loss per output of a multilabel classifier.
 
CategoryCrossEntropyLoss 
Categorical crossentropy loss for multiclass problems,
also known as the logistic loss for softmax (categorical) outputs.
 
HammingLoss 
Mean Accuracy loss, also known as zerooneloss per
class. Equivalent to ZeroOneLoss but
for multilabel classifiers.
 
HingeLoss 
Hinge loss.
 
LogisticLoss 
Logistic loss.
 
LogLikelihoodLoss 
Negative loglikelihood loss.
 
LossBaseT 
Base class for loss functions.
 
LossBaseTInput, TOutput 
Base class for loss functions.
 
RSquaredLoss 
R² (rsquared) loss.
 
SquareLoss 
Square loss, also known as L2loss.
 
ZeroOneLoss 
Accuracy loss, also known as zerooneloss.

Interface  Description  

ILossT  
ILossTInput, TOutput 
Common interface for loss functions, such as SquareLoss,
HingeLoss, CategoryCrossEntropyLoss and
BinaryCrossEntropyLoss.
