org.deeplearning4j.nn.conf.layers.samediff

Class AbstractSameDiffLayer.Builder<T extends AbstractSameDiffLayer.Builder<T>>

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer.Builder<T>

org.deeplearning4j.nn.conf.layers.samediff.AbstractSameDiffLayer.Builder<T>

Direct Known Subclasses:

SameDiffLayer.Builder

Enclosing class:

AbstractSameDiffLayer

public abstract static class AbstractSameDiffLayer.Builder<T extends AbstractSameDiffLayer.Builder<T>>
extends Layer.Builder<T>

Field Summary

Fields

Modifier and Type	Field and Description
protected IUpdater	biasUpdater Gradient updater configuration, for the biases only.
protected List<Regularization>	regularization
protected List<Regularization>	regularizationBias
protected IUpdater	updater Gradient updater.

Fields inherited from class org.deeplearning4j.nn.conf.layers.Layer.Builder

allParamConstraints, biasConstraints, iDropout, layerName, weightConstraints

Constructor Summary

Constructors

Constructor and Description
Builder()

Method Summary

Modifier and Type	Method and Description
T	biasUpdater(IUpdater biasUpdater) Gradient updater configuration, for the biases only.
T	l1(double l1) L1 regularization coefficient (weights only).
T	l1Bias(double l1Bias) L1 regularization coefficient for the bias.
T	l2(double l2) L2 regularization coefficient (weights only).
T	l2Bias(double l2Bias) L2 regularization coefficient for the bias.
AbstractSameDiffLayer.Builder	regularization(List<Regularization> regularization) Set the regularization for the parameters (excluding biases) - for example WeightDecay
AbstractSameDiffLayer.Builder	regularizationBias(List<Regularization> regularizationBias) Set the regularization for the biases only - for example WeightDecay
T	updater(IUpdater updater) Gradient updater.
AbstractSameDiffLayer.Builder	weightDecay(double coefficient) Add weight decay regularization for the network parameters (excluding biases). This applies weight decay with multiplying the learning rate - see WeightDecay for more details.
AbstractSameDiffLayer.Builder	weightDecay(double coefficient, boolean applyLR) Add weight decay regularization for the network parameters (excluding biases).
AbstractSameDiffLayer.Builder	weightDecayBias(double coefficient) Weight decay for the biases only - see weightDecay(double) for more details.
AbstractSameDiffLayer.Builder	weightDecayBias(double coefficient, boolean applyLR) Weight decay for the biases only - see weightDecay(double) for more details

Methods inherited from class org.deeplearning4j.nn.conf.layers.Layer.Builder

build, constrainAllParameters, constrainBias, constrainWeights, dropOut, dropOut, name

Methods inherited from class java.lang.Object

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

Field Detail

regularization

protected List<Regularization> regularization

regularizationBias

protected List<Regularization> regularizationBias

updater

protected IUpdater updater

Gradient updater. For example, Adam or Nesterovs

biasUpdater

protected IUpdater biasUpdater

Gradient updater configuration, for the biases only. If not set, biases will use the updater as set by updater(IUpdater)

Constructor Detail

Builder

public Builder()

Method Detail

l1

public T l1(double l1)

L1 regularization coefficient (weights only). Use l1Bias(double) to configure the l1 regularization coefficient for the bias.

l2

public T l2(double l2)

L2 regularization coefficient (weights only). Use l2Bias(double) to configure the l2 regularization coefficient for the bias.
Note: Generally, WeightDecay (set via weightDecay(double,boolean) should be preferred to L2 regularization. See WeightDecay javadoc for further details.

l1Bias

public T l1Bias(double l1Bias)

L1 regularization coefficient for the bias. Default: 0. See also l1(double)

l2Bias

public T l2Bias(double l2Bias)

L2 regularization coefficient for the bias. Default: 0. See also l2(double)
Note: Generally, WeightDecay (set via weightDecayBias(double,boolean) should be preferred to L2 regularization. See WeightDecay javadoc for further details.

weightDecay

public AbstractSameDiffLayer.Builder weightDecay(double coefficient)

Add weight decay regularization for the network parameters (excluding biases).
This applies weight decay with multiplying the learning rate - see WeightDecay for more details.

Parameters:

coefficient - Weight decay regularization coefficient

See Also:

weightDecay(double, boolean)

weightDecay

public AbstractSameDiffLayer.Builder weightDecay(double coefficient,
                                                 boolean applyLR)

Add weight decay regularization for the network parameters (excluding biases). See WeightDecay for more details.

Parameters:

coefficient - Weight decay regularization coefficient

applyLR - Whether the learning rate should be multiplied in when performing weight decay updates. See WeightDecay for more details.

See Also:

weightDecay(double, boolean)

weightDecayBias

public AbstractSameDiffLayer.Builder weightDecayBias(double coefficient)

Weight decay for the biases only - see weightDecay(double) for more details. This applies weight decay with multiplying the learning rate.

Parameters:

coefficient - Weight decay regularization coefficient

See Also:

weightDecayBias(double, boolean)

weightDecayBias

public AbstractSameDiffLayer.Builder weightDecayBias(double coefficient,
                                                     boolean applyLR)

Weight decay for the biases only - see weightDecay(double) for more details

Parameters:

coefficient - Weight decay regularization coefficient

regularization

public AbstractSameDiffLayer.Builder regularization(List<Regularization> regularization)

Set the regularization for the parameters (excluding biases) - for example WeightDecay

Parameters:

regularization - Regularization to apply for the network parameters/weights (excluding biases)

regularizationBias

public AbstractSameDiffLayer.Builder regularizationBias(List<Regularization> regularizationBias)

Set the regularization for the biases only - for example WeightDecay

Parameters:

regularizationBias - Regularization to apply for the network biases only

updater

public T updater(IUpdater updater)

Gradient updater. For example, Adam or Nesterovs

Parameters:

updater - Updater to use

biasUpdater

public T biasUpdater(IUpdater biasUpdater)

Gradient updater configuration, for the biases only. If not set, biases will use the updater as set by updater(IUpdater)

Parameters:

biasUpdater - Updater to use for bias parameters