public class Dropout extends AComponent
| Modifier and Type | Field and Description |
|---|---|
protected mikera.vectorz.Vector |
input |
protected mikera.vectorz.Vector |
inputGradient |
protected mikera.vectorz.Vector |
output |
protected mikera.vectorz.Vector |
outputGradient |
| Constructor and Description |
|---|
Dropout(int length) |
Dropout(int length,
double dropoutRate) |
| Modifier and Type | Method and Description |
|---|---|
Dropout |
clone()
Creates a clone of a module, including a deep copy of any mutable state.
|
List<IComponent> |
getComponents() |
mikera.vectorz.AVector |
getGradient()
Return an AVector referencing the accumulated gradient in this model
|
mikera.vectorz.Vector |
getInput() |
mikera.vectorz.Vector |
getInputGradient() |
IInputState |
getInputState() |
mikera.vectorz.Vector |
getOutput() |
mikera.vectorz.Vector |
getOutputGradient() |
mikera.vectorz.AVector |
getParameters()
Return an AVector referring to the parameters in the model.
|
void |
setInput(mikera.vectorz.AVector input) |
void |
thinkInternal()
Thinks within the scope of the component.
|
void |
thinkInternalTraining()
Thinks within the scope of the component.
|
void |
trainGradientInternal(double factor) |
applyConstraints, generate, generate, getComponent, getInputLength, getModules, getOutputLength, getParameterLength, isStochastic, setOutput, think, think, topComponent, train, train, trainGradientprotected final mikera.vectorz.Vector input
protected final mikera.vectorz.Vector inputGradient
protected final mikera.vectorz.Vector output
protected final mikera.vectorz.Vector outputGradient
public Dropout(int length)
public Dropout(int length,
double dropoutRate)
public void thinkInternal()
IComponentpublic void thinkInternalTraining()
IComponentthinkInternalTraining in interface IComponentthinkInternalTraining in interface ITrainablethinkInternalTraining in class AComponentpublic mikera.vectorz.AVector getParameters()
IParameterisedpublic mikera.vectorz.AVector getGradient()
IParameterisedpublic void trainGradientInternal(double factor)
trainGradientInternal in interface IComponenttrainGradientInternal in class AComponentpublic Dropout clone()
IModuleclone in interface IComponentclone in interface IModuleclone in interface IParameterisedclone in interface IThinkerclone in interface ITrainableclone in class AComponentpublic IInputState getInputState()
getInputState in interface IComponentgetInputState in class AComponentpublic mikera.vectorz.Vector getInput()
public mikera.vectorz.Vector getOutput()
public mikera.vectorz.Vector getOutputGradient()
public void setInput(mikera.vectorz.AVector input)
setInput in interface IInputStatesetInput in class AComponentpublic mikera.vectorz.Vector getInputGradient()
public List<IComponent> getComponents()
Copyright © 2013. All Rights Reserved.