org.deeplearning4j.optimize.optimizers

Class BackPropROptimizer

java.lang.Object

org.deeplearning4j.optimize.optimizers.BackPropROptimizer

All Implemented Interfaces:

Serializable, OptimizableByGradientValueMatrix

public class BackPropROptimizer
extends Object
implements Serializable, OptimizableByGradientValueMatrix

Optimizes via back prop gradients with the r operator, used in hessian free operators

Author:

Adam Gibson

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
BackPropROptimizer(BaseMultiLayerNetwork network, double lr, int epochs)

Method Summary

Modifier and Type	Method and Description
int	getNumParameters()
double	getParameter(int index)
org.nd4j.linalg.api.ndarray.INDArray	getParameters()
void	getParameters(double[] buffer)
double	getValue()
void	getValueGradient(double[] buffer)
org.nd4j.linalg.api.ndarray.INDArray	getValueGradient(int iteration)
void	optimize(TrainingEvaluator eval, int numEpochs, boolean lineSearch)
void	setCurrentIteration(int value)
void	setParameter(int index, double value)
void	setParameters(double[] params)
void	setParameters(org.nd4j.linalg.api.ndarray.INDArray params)

Methods inherited from class java.lang.Object

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

Constructor Detail

BackPropROptimizer

public BackPropROptimizer(BaseMultiLayerNetwork network,
                          double lr,
                          int epochs)

Method Detail

setCurrentIteration

public void setCurrentIteration(int value)

Specified by:

setCurrentIteration in interface OptimizableByGradientValueMatrix

optimize

public void optimize(TrainingEvaluator eval,
                     int numEpochs,
                     boolean lineSearch)

getValueGradient

public void getValueGradient(double[] buffer)

getValue

public double getValue()

Specified by:

getValue in interface OptimizableByGradientValueMatrix

getNumParameters

public int getNumParameters()

Specified by:

getNumParameters in interface OptimizableByGradientValueMatrix

getParameters

public void getParameters(double[] buffer)

getParameter

public double getParameter(int index)

Specified by:

getParameter in interface OptimizableByGradientValueMatrix

setParameters

public void setParameters(double[] params)

getParameters

public org.nd4j.linalg.api.ndarray.INDArray getParameters()

Specified by:

getParameters in interface OptimizableByGradientValueMatrix

setParameters

public void setParameters(org.nd4j.linalg.api.ndarray.INDArray params)

Specified by:

setParameters in interface OptimizableByGradientValueMatrix

setParameter

public void setParameter(int index,
                         double value)

Specified by:

setParameter in interface OptimizableByGradientValueMatrix

getValueGradient

public org.nd4j.linalg.api.ndarray.INDArray getValueGradient(int iteration)

Specified by:

getValueGradient in interface OptimizableByGradientValueMatrix