| Package | Description |
|---|---|
| org.deeplearning4j.arbiter.layers | |
| org.deeplearning4j.nn.conf.ocnn |
| Modifier and Type | Method and Description |
|---|---|
protected void |
OCNNLayerSpace.setLayerOptionsBuilder(OCNNOutputLayer.Builder builder,
double[] values) |
| Modifier and Type | Method and Description |
|---|---|
OCNNOutputLayer.Builder |
OCNNOutputLayer.Builder.activation(IActivation activation)
The activation function to use with ocnn
|
OCNNOutputLayer.Builder |
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 |
OCNNOutputLayer.Builder.hiddenLayerSize(int hiddenLayerSize)
The hidden layer size for the one class neural network.
|
OCNNOutputLayer.Builder |
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 |
OCNNOutputLayer.Builder.nOut(int nOut) |
OCNNOutputLayer.Builder |
OCNNOutputLayer.Builder.nu(double nu)
For nu definition see the paper
|
OCNNOutputLayer.Builder |
OCNNOutputLayer.Builder.windowSize(int windowSize)
The number of examples to use for computing the quantile for the r value update.
|
| Constructor and Description |
|---|
OCNNOutputLayer(OCNNOutputLayer.Builder builder) |
Copyright © 2020. All rights reserved.