nuroko.module

Class NeuralNet

java.lang.Object

nuroko.module.AComponent

nuroko.module.ALayerStack

nuroko.module.NeuralNet

All Implemented Interfaces:

Cloneable, Iterable<IComponent>, IComponent, IFunction<mikera.vectorz.AVector,mikera.vectorz.AVector>, IInput, IInputOutput, IInputState, IModule, IOutput, IOutputState, IParameterised, ISynthesiser, IThinker, ITrainable

public class NeuralNet
extends ALayerStack

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)
NeuralNet(AWeightLayer layer, mikera.vectorz.Op outputOp)

Method Summary

Methods

Modifier and Type	Method and Description
void	applyConstraintsInternal()
NeuralNet	clone() Creates a clone of a module, including a deep copy of any mutable state.
List<IComponent>	getComponents()
mikera.vectorz.AVector	getData(int i)
LossFunction	getDefaultLossFunction() Returns the default loss function that should be used
mikera.vectorz.AVector	getGradient() Return an AVector referencing the accumulated gradient in this model
mikera.vectorz.AVector	getInput()
mikera.vectorz.AVector	getInputGradient()
int	getInputLength()
NeuralNet	getInverse()
AWeightLayer	getLayer(int i)
int	getLayerCount()
mikera.vectorz.Op	getLayerOp(int i)
List<AWeightLayer>	getLayers()
List<IModule>	getModules() Returns a list of sub-components of this module
mikera.vectorz.AVector	getOutput()
mikera.vectorz.AVector	getOutputGradient()
int	getOutputLength()
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.
boolean	hasDifferentTrainingThinking()
void	initRandom() Randomly initialises a component's parameters
void	thinkInternal() Thinks within the scope of the component.
void	trainGradientInternal(double factor) Abstract method for training gradients.

Methods inherited from class nuroko.module.ALayerStack

subStack

Methods inherited from class nuroko.module.AComponent

applyConstraints, generate, generate, getComponent, getConstraints, getDownStack, getInputState, getLearnFactor, getUpStack, isStochastic, isSynthesiser, iterator, setConstraint, setInput, setLearnFactor, setOutput, think, think, thinkInternalTraining, topComponent, train, train, trainSynth, trainSynth

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 layer,
         mikera.vectorz.Op outputOp)

NeuralNet

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

Method Detail

getModules

public List<IModule> getModules()

Description copied from interface: IModule

Returns a list of sub-components of this module

Specified by:

getModules in interface IModule

Overrides:

getModules in class AComponent

Returns:

getDefaultLossFunction

public LossFunction getDefaultLossFunction()

Description copied from interface: IComponent

Returns the default loss function that should be used

Specified by:

getDefaultLossFunction in interface IComponent

Overrides:

getDefaultLossFunction in class AComponent

Returns:

getComponents

public List<IComponent> getComponents()

getInverse

public NeuralNet getInverse()

initRandom

public void initRandom()

Description copied from interface: IComponent

Randomly initialises a component's parameters

Specified by:

initRandom in interface IComponent

Overrides:

initRandom in class AComponent

trainGradientInternal

public void trainGradientInternal(double factor)

Description copied from class: AComponent

Abstract method for training gradients. Assumes use of the current activation states for all inputs/outputs. Should overwrite inputGradient, and adjust gradient for all parameters. Should apply own internal learn rate factor

Specified by:

trainGradientInternal in interface IComponent

Specified by:

trainGradientInternal in class AComponent

getLayerOp

public mikera.vectorz.Op getLayerOp(int i)

thinkInternal

public void thinkInternal()

Description copied from interface: IComponent

Thinks within the scope of the component. Updates component's output.

getLayer

public AWeightLayer getLayer(int i)

Specified by:

getLayer in class ALayerStack

getInputLength

public int getInputLength()

Specified by:

getInputLength in interface IInput

Overrides:

getInputLength in class AComponent

getOutputLength

public int getOutputLength()

Specified by:

getOutputLength in interface IOutput

Overrides:

getOutputLength in class AComponent

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 AComponent

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.

Returns:

getGradient

public mikera.vectorz.AVector getGradient()

Description copied from interface: IParameterised

Return an AVector referencing the accumulated gradient in this model

Returns:

getLayers

public List<AWeightLayer> getLayers()

Overrides:

getLayers in class ALayerStack

applyConstraintsInternal

public void applyConstraintsInternal()

Overrides:

applyConstraintsInternal in class AComponent

getOutput

public mikera.vectorz.AVector getOutput()

Specified by:

getOutput in interface IOutputState

Overrides:

getOutput in class ALayerStack

getInput

public mikera.vectorz.AVector getInput()

Specified by:

getInput in interface IInputState

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 IComponent

Specified by:

clone in interface IModule

Specified by:

clone in interface IParameterised

Specified by:

clone in interface ISynthesiser

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

getInputGradient

public mikera.vectorz.AVector getInputGradient()

getOutputGradient

public mikera.vectorz.AVector getOutputGradient()

hasDifferentTrainingThinking

public boolean hasDifferentTrainingThinking()