org.nd4j.linalg.learning

Class AdaDelta

java.lang.Object

org.nd4j.linalg.learning.AdaDelta

All Implemented Interfaces:

Serializable, GradientUpdater

public class AdaDelta
extends Object
implements Serializable, GradientUpdater

http://www.matthewzeiler.com/pubs/googleTR2012/googleTR2012.pdf Ada delta updater. More robust adagrad that keeps track of a moving window average of the gradient rather than the every decaying learning rates of adagrad

Author:

Adam Gibson

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	AdaDelta.AdaDeltaAggregator

Constructor Summary

Constructors

Constructor and Description
AdaDelta(double rho)

Method Summary

Modifier and Type	Method and Description
GradientUpdaterAggregator	getAggregator(boolean addThis) Get a GradientUpdaterAggregator.
INDArray	getGradient(INDArray gradient, int iteration) Get the updated gradient for the given gradient and also update the state of ada delta.
void	update(Object... args) update(learningRate,momentum)

Methods inherited from class java.lang.Object

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

Constructor Detail

AdaDelta

public AdaDelta(double rho)

Method Detail

update

public void update(Object... args)

Description copied from interface: GradientUpdater

update(learningRate,momentum)

Specified by:

update in interface GradientUpdater

getGradient

public INDArray getGradient(INDArray gradient,
                            int iteration)

Get the updated gradient for the given gradient and also update the state of ada delta.

Specified by:

getGradient in interface GradientUpdater

Parameters:

gradient - the gradient to get the updated gradient for

iteration -

Returns:

the update gradient

getAggregator

public GradientUpdaterAggregator getAggregator(boolean addThis)

Description copied from interface: GradientUpdater

Get a GradientUpdaterAggregator. The aggregator is used (typically in distributed learning scenarios) to combine separate GradientUpdater instances for different networks (usually by averaging).

Specified by:

getAggregator in interface GradientUpdater

Parameters:

addThis - If true: return a GradientUpdaterAggregator with the GradientUpdater already added. If false: return an empty (uninitialized) GradientUpdaterAggregator