public static class OCNNOutputLayer.Builder extends BaseOutputLayer.Builder<OCNNOutputLayer.Builder>
Modifier and Type | Field and Description |
---|---|
protected IActivation |
activation |
protected boolean |
configureR |
protected int |
hiddenLayerSize |
protected double |
initialRValue |
protected double |
nu |
protected int |
windowSize |
lossFn
nIn, nOut
activationFn, biasInit, biasUpdater, dist, gradientNormalization, gradientNormalizationThreshold, iupdater, l1, l1Bias, l2, l2Bias, weightInit, weightNoise
allParamConstraints, biasConstraints, iDropout, layerName, weightConstraints
Constructor and Description |
---|
Builder() |
Modifier and Type | Method and Description |
---|---|
OCNNOutputLayer.Builder |
activation(IActivation activation)
The activation function to use with ocnn
|
OCNNOutputLayer |
build() |
OCNNOutputLayer.Builder |
configureR(boolean configureR)
Whether to use the specified
initialRValue or
use the weight initialization with
the neural network for the r value |
OCNNOutputLayer.Builder |
hiddenLayerSize(int hiddenLayerSize)
The hidden layer size for the one class neural network.
|
OCNNOutputLayer.Builder |
initialRValue(double initialRValue)
The initial r value to use for ocnn
for definition, see the paper,
note this is only active when
configureR
is specified as true |
OCNNOutputLayer.Builder |
nOut(int nOut)
Number of outputs - used to set the layer size (number of units/nodes for the current layer).
|
OCNNOutputLayer.Builder |
nu(double nu)
For nu definition see the paper
|
OCNNOutputLayer.Builder |
windowSize(int windowSize)
The number of examples to use for computing the
quantile for the r value update.
|
hasBias, lossFunction, lossFunction
nIn, nIn, nOut, units
activation, biasInit, biasUpdater, dist, gradientNormalization, gradientNormalizationThreshold, l1, l1Bias, l2, l2Bias, updater, updater, weightInit, weightInit, weightNoise
constrainAllParameters, constrainBias, constrainWeights, dropOut, dropOut, name
protected int hiddenLayerSize
protected double nu
protected int windowSize
protected IActivation activation
protected double initialRValue
protected boolean configureR
public OCNNOutputLayer.Builder configureR(boolean configureR)
initialRValue
or
use the weight initialization with
the neural network for the r valueconfigureR
- true if we should use the
initial initialRValue
public OCNNOutputLayer.Builder initialRValue(double initialRValue)
configureR
is specified as trueinitialRValue
- the intpublic OCNNOutputLayer.Builder windowSize(int windowSize)
windowSize
- the number of examples to use
for computing the quantile
of the dataset for the r value updatepublic OCNNOutputLayer.Builder nu(double nu)
nu
- the nu for ocnnpublic OCNNOutputLayer.Builder activation(IActivation activation)
activation
in class BaseLayer.Builder<OCNNOutputLayer.Builder>
activation
- the activation function to suepublic OCNNOutputLayer.Builder hiddenLayerSize(int hiddenLayerSize)
hiddenLayerSize
- the hidden layer size to use
with ocnnpublic OCNNOutputLayer.Builder nOut(int nOut)
FeedForwardLayer.Builder
FeedForwardLayer.Builder.units(int)
nOut
in class FeedForwardLayer.Builder<OCNNOutputLayer.Builder>
nOut
- Number of outputs / layer sizepublic OCNNOutputLayer build()
build
in class Layer.Builder<OCNNOutputLayer.Builder>
Copyright © 2018. All rights reserved.