nuroko.module

Class Stack

java.lang.Object

nuroko.module.AComponent

nuroko.module.ACompoundComponent

nuroko.module.Stack

All Implemented Interfaces:

Cloneable, IComponent, IGradientTrainable, IInput, IInputOutput, IInputState, IModule, IOutput, IOutputState, IParameterised, IThinker, ITrainable

public class Stack
extends ACompoundComponent

A stack of connected components, with the output of each feeding into the input of the next

Author:

Mike

Field Summary

Fields inherited from class nuroko.module.ACompoundComponent

componentCount, components, gradient, parameters

Constructor Summary

Constructors

Constructor and Description
Stack(List<? extends IComponent> comps)

Method Summary

Methods

Modifier and Type	Method and Description
Stack	clone() Creates a clone of a module, including a deep copy of any mutable state.
mikera.vectorz.AVector	getInput()
mikera.vectorz.AVector	getInputGradient()
int	getInputLength()
IInputState	getInputState()
mikera.vectorz.AVector	getOutput()
mikera.vectorz.AVector	getOutputGradient()
void	setInput(mikera.vectorz.AVector input)
void	thinkInternal() Thinks within the scope of the component.
IComponent	topComponent()
void	trainGradient(mikera.vectorz.AVector gradient, double factor) Trains with a output gradient, incrementing inputGradient and accumulated gradient for parameters.
void	trainGradientInternal(double factor)

Methods inherited from class nuroko.module.ACompoundComponent

getComponent, getComponents, getGradient, getParameterLength, getParameters

Methods inherited from class nuroko.module.AComponent

getModules, getOutputLength, isStochastic, setOutput, think, think, thinkInternalTraining, train, train

Methods inherited from class java.lang.Object

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

Constructor Detail

Stack

public Stack(List<? extends IComponent> comps)

Method Detail

topComponent

public IComponent topComponent()

Overrides:

topComponent in class AComponent

getInput

public mikera.vectorz.AVector getInput()

getInputGradient

public mikera.vectorz.AVector getInputGradient()

getInputLength

public int getInputLength()

Specified by:

getInputLength in interface IInput

Overrides:

getInputLength in class AComponent

thinkInternal

public void thinkInternal()

Description copied from interface: IComponent

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

clone

public Stack 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 IThinker

Specified by:

clone in interface ITrainable

Specified by:

clone in class AComponent

Returns:

setInput

public void setInput(mikera.vectorz.AVector input)

Specified by:

setInput in interface IInputState

Overrides:

setInput in class AComponent

getInputState

public IInputState getInputState()

Specified by:

getInputState in interface IComponent

Overrides:

getInputState in class AComponent

trainGradient

public void trainGradient(mikera.vectorz.AVector gradient,
                 double factor)

Description copied from interface: IGradientTrainable

Trains with a output gradient, incrementing inputGradient and accumulated gradient for parameters.

factor - TODO

trainGradientInternal

public void trainGradientInternal(double factor)

getOutput

public mikera.vectorz.AVector getOutput()

getOutputGradient

public mikera.vectorz.AVector getOutputGradient()