| Package | Description |
|---|---|
| de.jungblut.classification.nn | |
| de.jungblut.math.loss |
| Modifier and Type | Field and Description |
|---|---|
LossFunction |
MultilayerPerceptronCostFunction.NetworkConfiguration.error |
| Modifier and Type | Method and Description |
|---|---|
static MultilayerPerceptron.MultilayerPerceptronBuilder |
MultilayerPerceptron.MultilayerPerceptronBuilder.create(int[] layer,
ActivationFunction[] activations,
LossFunction errorFunction,
Minimizer minimizer,
int maxIteration)
Creates a new TrainingConfiguration with the mandatory configurations of
the activation functions, the to be used minimizer and the maximum
iterations.
|
| Modifier and Type | Class and Description |
|---|---|
class |
CrossEntropyLoss
Cross entropy error function, for example to be used with the
SoftMaxActivationFunction. |
class |
HingeLoss
Hinge-loss for linear SVMs.
|
class |
LogLoss
Logistic error function implementation.
|
class |
SquaredLoss
Squared mean error function for regression problems and
LinearActivationFunction. |
class |
StepLoss
Calculates a step error function that can be used for
StepActivationFunction. |
Copyright © 2016. All rights reserved.