org.deeplearning4j.util

Class NonZeroStoppingConjugateGradient

java.lang.Object

org.deeplearning4j.util.NonZeroStoppingConjugateGradient

All Implemented Interfaces:

cc.mallet.optimize.Optimizer

public class NonZeroStoppingConjugateGradient
extends Object
implements cc.mallet.optimize.Optimizer

Modified based on cc.mallet.optimize.ConjugateGradient

no termination when zero tolerance

Since:

2013-08-25

Author:

GuoDing

Nested Class Summary

Nested classes/interfaces inherited from interface cc.mallet.optimize.Optimizer

cc.mallet.optimize.Optimizer.ByBatches

Constructor Summary

Constructors

Constructor and Description
NonZeroStoppingConjugateGradient(cc.mallet.optimize.Optimizable.ByGradientValue function)
NonZeroStoppingConjugateGradient(cc.mallet.optimize.Optimizable.ByGradientValue function, double initialStepSize)
NonZeroStoppingConjugateGradient(cc.mallet.optimize.Optimizable.ByGradientValue function, double initialStepSize, NeuralNetEpochListener listener)
NonZeroStoppingConjugateGradient(cc.mallet.optimize.Optimizable.ByGradientValue function, NeuralNetEpochListener listener)

Method Summary

Methods

Modifier and Type	Method and Description
double	getInitialStepSize()
int	getMaxIterations()
cc.mallet.optimize.Optimizable	getOptimizable()
double	getStepSize()
boolean	isConverged()
boolean	optimize()
boolean	optimize(int numIterations)
void	reset()
void	setEvaluator(cc.mallet.optimize.OptimizerEvaluator.ByGradient eval)
void	setInitialStepSize(double initialStepSize)
void	setLineMaximizer(cc.mallet.optimize.LineOptimizer.ByGradient lineMaximizer)
void	setMaxIterations(int maxIterations)
void	setTolerance(double t)

Methods inherited from class java.lang.Object

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

Constructor Detail

NonZeroStoppingConjugateGradient

public NonZeroStoppingConjugateGradient(cc.mallet.optimize.Optimizable.ByGradientValue function,
                                double initialStepSize)

NonZeroStoppingConjugateGradient

public NonZeroStoppingConjugateGradient(cc.mallet.optimize.Optimizable.ByGradientValue function,
                                NeuralNetEpochListener listener)

NonZeroStoppingConjugateGradient

public NonZeroStoppingConjugateGradient(cc.mallet.optimize.Optimizable.ByGradientValue function,
                                double initialStepSize,
                                NeuralNetEpochListener listener)

NonZeroStoppingConjugateGradient

public NonZeroStoppingConjugateGradient(cc.mallet.optimize.Optimizable.ByGradientValue function)

Method Detail

getOptimizable

public cc.mallet.optimize.Optimizable getOptimizable()

Specified by:

getOptimizable in interface cc.mallet.optimize.Optimizer

isConverged

public boolean isConverged()

Specified by:

isConverged in interface cc.mallet.optimize.Optimizer

setEvaluator

public void setEvaluator(cc.mallet.optimize.OptimizerEvaluator.ByGradient eval)

setLineMaximizer

public void setLineMaximizer(cc.mallet.optimize.LineOptimizer.ByGradient lineMaximizer)

setInitialStepSize

public void setInitialStepSize(double initialStepSize)

getInitialStepSize

public double getInitialStepSize()

getStepSize

public double getStepSize()

optimize

public boolean optimize()

Specified by:

optimize in interface cc.mallet.optimize.Optimizer

setTolerance

public void setTolerance(double t)

optimize

public boolean optimize(int numIterations)

Specified by:

optimize in interface cc.mallet.optimize.Optimizer

reset

public void reset()

getMaxIterations

public int getMaxIterations()

setMaxIterations

public void setMaxIterations(int maxIterations)