org.nd4j.linalg.learning.config

Class RmsProp

java.lang.Object

org.nd4j.linalg.learning.config.RmsProp

All Implemented Interfaces:

Serializable, Cloneable, IUpdater

public class RmsProp
extends Object
implements IUpdater

RMS Prop updates:

http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf http://cs231n.github.io/neural-networks-3/#ada

Author:

Adam Gibson

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	RmsProp.Builder

Field Summary

Fields

Modifier and Type	Field and Description
static double	DEFAULT_RMSPROP_EPSILON
static double	DEFAULT_RMSPROP_LEARNING_RATE
static double	DEFAULT_RMSPROP_RMSDECAY

Constructor Summary

Constructors

Constructor and Description
RmsProp()
RmsProp(double rmsDecay)

Method Summary

Modifier and Type	Method and Description
void	applySchedules(int iteration, double newLearningRate) Apply the new learning rate and any other schedules
RmsProp	clone() Clone the updater
GradientUpdater	instantiate(INDArray viewArray, boolean initializeViewArray) Create a new gradient updater
long	stateSize(long numParams) Determine the updater state size for the given number of parameters.

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.nd4j.linalg.learning.config.IUpdater

equals

Field Detail

DEFAULT_RMSPROP_LEARNING_RATE

public static final double DEFAULT_RMSPROP_LEARNING_RATE

See Also:

Constant Field Values

DEFAULT_RMSPROP_EPSILON

public static final double DEFAULT_RMSPROP_EPSILON

See Also:

Constant Field Values

DEFAULT_RMSPROP_RMSDECAY

public static final double DEFAULT_RMSPROP_RMSDECAY

See Also:

Constant Field Values

Constructor Detail

RmsProp

public RmsProp()

RmsProp

public RmsProp(double rmsDecay)

Method Detail

stateSize

public long stateSize(long numParams)

Description copied from interface: IUpdater

Determine the updater state size for the given number of parameters. Usually a integer multiple (0,1 or 2) times the number of parameters in a layer.

Specified by:

stateSize in interface IUpdater

Parameters:

numParams - Number of parameters

Returns:

Updater state size for the given number of parameters

applySchedules

public void applySchedules(int iteration,
                           double newLearningRate)

Description copied from interface: IUpdater

Apply the new learning rate and any other schedules

Specified by:

applySchedules in interface IUpdater

Parameters:

iteration - Current iteration count

newLearningRate - new learning rate to set for the updater

instantiate

public GradientUpdater instantiate(INDArray viewArray,
                                   boolean initializeViewArray)

Description copied from interface: IUpdater

Create a new gradient updater

Specified by:

instantiate in interface IUpdater

Parameters:

viewArray - The updater state size view away

initializeViewArray - If true: initialise the updater state

Returns:

clone

public RmsProp clone()

Description copied from interface: IUpdater

Clone the updater

Specified by:

clone in interface IUpdater

Overrides:

clone in class Object