public class NetworkStack extends CompoundStack<ALayerStack> implements ITrainable
componentCount, components| Constructor and Description |
|---|
NetworkStack(ALayerStack... components) |
NetworkStack(List<ALayerStack> components) |
| Modifier and Type | Method and Description |
|---|---|
NetworkStack |
clone()
Creates a clone of a module, including a deep copy of any mutable state.
|
mikera.vectorz.AVector |
getData(int i) |
int |
getInputLength() |
AWeightLayer |
getLayer(int i) |
int |
getLayerCount() |
int |
getOutputLength() |
void |
think(mikera.vectorz.AVector input,
mikera.vectorz.AVector output) |
void |
train(mikera.vectorz.AVector input,
mikera.vectorz.AVector target) |
void |
trainGradient(mikera.vectorz.AVector input,
mikera.vectorz.AVector outputGradient,
mikera.vectorz.AVector inputGradient,
double factor,
boolean skipTopDerivative)
Trains with a direct gradient.
|
getComponent, getComponents, getGradient, getParametersgetInput, getLayers, getOutput, getParameterLengthequals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitgetComponentsgetGradient, getParameterLength, getParameterspublic NetworkStack(ALayerStack... components)
public NetworkStack(List<ALayerStack> components)
public int getInputLength()
getInputLength in interface IInputpublic int getOutputLength()
getOutputLength in interface IOutputpublic void think(mikera.vectorz.AVector input,
mikera.vectorz.AVector output)
think in interface IThinkerthink in class CompoundStack<ALayerStack>public int getLayerCount()
getLayerCount in class CompoundStack<ALayerStack>public AWeightLayer getLayer(int i)
getLayer in class CompoundStack<ALayerStack>public mikera.vectorz.AVector getData(int i)
getData in class CompoundStack<ALayerStack>public NetworkStack clone()
IModuleclone in interface IModuleclone in interface IParameterisedclone in interface IThinkerclone in interface ITrainableclone in class CompoundStack<ALayerStack>public void train(mikera.vectorz.AVector input,
mikera.vectorz.AVector target)
train in interface ITrainabletrain in class ALayerStackpublic void trainGradient(mikera.vectorz.AVector input,
mikera.vectorz.AVector outputGradient,
mikera.vectorz.AVector inputGradient,
double factor,
boolean skipTopDerivative)
ALayerStacktrainGradient in class ALayerStackCopyright © 2013. All Rights Reserved.