Package deepnetts.net.loss

Interface LossFunction

All Known Implementing Classes:

BinaryCrossEntropyLoss, CrossEntropyLoss, MeanSquaredErrorLoss

public interface LossFunction

Base Interface for all loss functions. Loss function is a component of a deep learning algorithm which calculates an error, as a difference of actual (or predicted) and desired (target) output of a neural network. The total error for some training is usually calculated as a average of errors for all individual input-output pairs. The higher value of loss function, means higher error and lower accuracy of prediction.

See Also:

• MeanSquaredErrorLoss
• BinaryCrossEntropyLoss
• CrossEntropyLoss

Method Summary

Modifier and Type	Method	Description
float[]	addPatternError(float[] predictedOutput, float[] targetOutput)	Calculates pattern error for singe pattern for the specified predicted and target outputs, adds the error to total error, and returns the pattern error.
TensorBase	addPatternError(TensorBase predictedOutput, TensorBase targetOutput)
void	addRegularizationSum(float regSum)	Adds specified regularization sum to total loss.
float	getPatternLoss()
float	getTotal()	Returns the total error calculated by this loss function.
void	reset()	Resets the total error and pattern counter.
default float	valueFor(NeuralNetwork nnet, javax.visrec.ml.data.DataSet<? extends MLDataItem> dataSet)	Calculates and returns loss function value for the given neural network and data set.

Method Details

addPatternError

float[] addPatternError(float[] predictedOutput,
 float[] targetOutput)

Calculates pattern error for singe pattern for the specified predicted and target outputs, adds the error to total error, and returns the pattern error.

Parameters:

predictedOutput - predicted/actual network output vector

targetOutput - target network output vector

Returns:

error vector error vector for the given predicted and target vectors

addPatternError

TensorBase addPatternError(TensorBase predictedOutput,
 TensorBase targetOutput)

addRegularizationSum

void addRegularizationSum(float regSum)

Adds specified regularization sum to total loss.

Parameters:

regSum - regularization sum

getTotal

float getTotal()

Returns the total error calculated by this loss function.

Returns:

total error calculated by this loss function

getPatternLoss

float getPatternLoss()

reset

void reset()

Resets the total error and pattern counter.

valueFor

default float valueFor(NeuralNetwork nnet,
 javax.visrec.ml.data.DataSet<? extends MLDataItem> dataSet)

Calculates and returns loss function value for the given neural network and data set.

Parameters:

nnet -

dataSet -

Returns: