nuroko.core

Interface IComponent

All Superinterfaces:

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

All Known Implementing Classes:

AComponent, ACompoundComponent, ALayerStack, AOperationComponent, AWeightLayer, Bias, CompoundLayerStack, Dropout, FullWeightLayer, GradientAmplifier, Identity, Join, NeuralNet, Normaliser, Operator, SparseWeightLayer, Sparsifier, Stack, ThinkingOp, TrainingOp

public interface IComponent
extends ITrainable, IInputState, IOutputState, ISynthesiser

Method Summary

Modifier and Type	Method and Description
void	applyConstraints()
IComponent	clone() Creates a clone of a module, including a deep copy of any mutable state.
List<IComponent>	getComponents()
LossFunction	getDefaultLossFunction() Returns the default loss function that should be used
IInputState	getInputState()
double	getLearnFactor()
boolean	hasDifferentTrainingThinking()
void	initRandom() Randomly initialises a component's parameters
boolean	isStochastic()
boolean	isSynthesiser()
void	setLearnFactor(double d)
void	thinkInternal() Thinks within the scope of the component.
void	thinkInternalTraining() Thinks within the scope of the component.
void	trainGradientInternal(double factor)
void	trainSynth(mikera.vectorz.AVector input)

Methods inherited from interface nuroko.core.ITrainable

train, train

Methods inherited from interface nuroko.core.IThinker

think, think

Methods inherited from interface nuroko.core.IOutput

getOutputLength

Methods inherited from interface nuroko.core.IInput

getInputLength

Methods inherited from interface nuroko.core.IModule

getModules

Methods inherited from interface nuroko.core.IParameterised

getGradient, getParameterLength, getParameters

Methods inherited from interface nuroko.core.IInputState

getInput, getInputGradient, setInput

Methods inherited from interface nuroko.core.IOutputState

getOutput, getOutputGradient, setOutput

Methods inherited from interface nuroko.core.ISynthesiser

generate, generate, getDownStack, getUpStack, trainSynth

Method Detail

clone

IComponent 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 ISynthesiser

Specified by:

clone in interface IThinker

Specified by:

clone in interface ITrainable

getInputState

IInputState getInputState()

thinkInternal

void thinkInternal()

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

thinkInternalTraining

void thinkInternalTraining()

Thinks within the scope of the component. Update's component's output. May be different from regular thinking.

Specified by:

thinkInternalTraining in interface ITrainable

getDefaultLossFunction

LossFunction getDefaultLossFunction()

Returns the default loss function that should be used

Returns:

trainGradientInternal

void trainGradientInternal(double factor)

getLearnFactor

double getLearnFactor()

isStochastic

boolean isStochastic()

applyConstraints

void applyConstraints()

trainSynth

void trainSynth(mikera.vectorz.AVector input)

Specified by:

trainSynth in interface ISynthesiser

getComponents

List<IComponent> getComponents()

initRandom

void initRandom()

Randomly initialises a component's parameters

hasDifferentTrainingThinking

boolean hasDifferentTrainingThinking()

setLearnFactor

void setLearnFactor(double d)

isSynthesiser

boolean isSynthesiser()