nuroko.module

Class NeuralNet

java.lang.Object

nuroko.module.ALayerStack

nuroko.module.NeuralNet

All Implemented Interfaces:

Cloneable, IInput, IInputOutput, IModule, IOutput, IParameterised, IThinker, ITrainable

public class NeuralNet
extends ALayerStack
implements ITrainable

Constructor Summary

Constructors

Constructor and Description
NeuralNet(AWeightLayer... layers)
NeuralNet(AWeightLayer[] layers, mikera.vectorz.Op outputOp)
NeuralNet(AWeightLayer[] layers, mikera.vectorz.Op hiddenOp, mikera.vectorz.Op outputOp)

Method Summary

Methods

Modifier and Type	Method and Description
NeuralNet	clone() Creates a clone of a module, including a deep copy of any mutable state.
List<IModule>	getComponents() Returns a list of sub-components of this module
mikera.vectorz.AVector	getData(int i)
mikera.vectorz.AVector	getGradient() Return an AVector referencing the accumulated gradient in this model
mikera.vectorz.AVector	getInput()
int	getInputLength()
mikera.vectorz.AVector	getInputSignal()
NeuralNet	getInverse()
AWeightLayer	getLayer(int i)
int	getLayerCount()
mikera.vectorz.Op	getLayerOp(int i)
List<AWeightLayer>	getLayers()
mikera.vectorz.AVector	getOutput()
int	getOutputLength()
mikera.vectorz.AVector	getOutputSignal()
int	getParameterLength() Returns the length of the parameter vector for this model
mikera.vectorz.AVector	getParameters() Return an AVector referring to the parameters in the model.
void	initRandom()
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.

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

NeuralNet

public NeuralNet(AWeightLayer... layers)

NeuralNet

public NeuralNet(AWeightLayer[] layers,
         mikera.vectorz.Op outputOp)

NeuralNet

public NeuralNet(AWeightLayer[] layers,
         mikera.vectorz.Op hiddenOp,
         mikera.vectorz.Op outputOp)

Method Detail

getComponents

public List<IModule> getComponents()

Description copied from interface: IModule

Returns a list of sub-components of this module

Specified by:

getComponents in interface IModule

Returns:

getInverse

public NeuralNet getInverse()

initRandom

public void initRandom()

train

public void train(mikera.vectorz.AVector input,
         mikera.vectorz.AVector target)

Specified by:

train in interface ITrainable

Specified by:

train in class ALayerStack

trainGradient

public void trainGradient(mikera.vectorz.AVector input,
                 mikera.vectorz.AVector outputGradient,
                 mikera.vectorz.AVector inputGradient,
                 double factor,
                 boolean skipTopDerivative)

Description copied from class: ALayerStack

Trains with a direct gradient. Assumes think has been called immediately prior to set any intermediate values.

Specified by:

trainGradient in class ALayerStack

getLayerOp

public mikera.vectorz.Op getLayerOp(int i)

think

public void think(mikera.vectorz.AVector input,
         mikera.vectorz.AVector output)

Specified by:

think in interface IThinker

getLayer

public AWeightLayer getLayer(int i)

Specified by:

getLayer in class ALayerStack

getInputLength

public int getInputLength()

Specified by:

getInputLength in interface IInput

getOutputLength

public int getOutputLength()

Specified by:

getOutputLength in interface IOutput

getParameterLength

public int getParameterLength()

Description copied from interface: IParameterised

Returns the length of the parameter vector for this model

Specified by:

getParameterLength in interface IParameterised

Overrides:

getParameterLength in class ALayerStack

Returns:

getParameters

public mikera.vectorz.AVector getParameters()

Description copied from interface: IParameterised

Return an AVector referring to the parameters in the model. Expected to be mutable.

Specified by:

getParameters in interface IParameterised

Returns:

getGradient

public mikera.vectorz.AVector getGradient()

Description copied from interface: IParameterised

Return an AVector referencing the accumulated gradient in this model

Specified by:

getGradient in interface IParameterised

Returns:

getLayers

public List<AWeightLayer> getLayers()

Overrides:

getLayers in class ALayerStack

getInputSignal

public mikera.vectorz.AVector getInputSignal()

getOutputSignal

public mikera.vectorz.AVector getOutputSignal()

getOutput

public mikera.vectorz.AVector getOutput()

Overrides:

getOutput in class ALayerStack

getInput

public mikera.vectorz.AVector getInput()

Overrides:

getInput in class ALayerStack

getData

public mikera.vectorz.AVector getData(int i)

Specified by:

getData in class ALayerStack

clone

public NeuralNet clone()

Description copied from interface: IModule

Creates a clone of a module, including a deep copy of any mutable state.

Specified by:

clone in interface IModule

Specified by:

clone in interface IParameterised

Specified by:

clone in interface IThinker

Specified by:

clone in interface ITrainable

Specified by:

clone in class ALayerStack

Returns:

getLayerCount

public int getLayerCount()

Specified by:

getLayerCount in class ALayerStack