org.deeplearning4j.nn.conf.layers

Class AbstractLSTM

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer

org.deeplearning4j.nn.conf.layers.BaseLayer

org.deeplearning4j.nn.conf.layers.FeedForwardLayer

org.deeplearning4j.nn.conf.layers.BaseRecurrentLayer

org.deeplearning4j.nn.conf.layers.AbstractLSTM

All Implemented Interfaces:

Serializable, Cloneable

Direct Known Subclasses:

GravesLSTM, LSTM

public abstract class AbstractLSTM
extends BaseRecurrentLayer

LSTM recurrent net, based on Graves: Supervised Sequence Labelling with Recurrent Neural Networks http://www.cs.toronto.edu/~graves/phd.pdf

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	AbstractLSTM.Builder<T extends AbstractLSTM.Builder<T>>

Field Summary

Fields

Modifier and Type	Field and Description
protected double	forgetGateBiasInit
protected org.nd4j.linalg.activations.IActivation	gateActivationFn

Fields inherited from class org.deeplearning4j.nn.conf.layers.FeedForwardLayer

nIn, nOut

Fields inherited from class org.deeplearning4j.nn.conf.layers.BaseLayer

activationFn, adamMeanDecay, adamVarDecay, biasInit, biasLearningRate, dist, epsilon, gradientNormalization, gradientNormalizationThreshold, iUpdater, l1, l1Bias, l2, l2Bias, learningRate, learningRateSchedule, momentum, momentumSchedule, rho, rmsDecay, updater, weightInit

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

dropOut, layerName

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	AbstractLSTM(AbstractLSTM.Builder builder)

Method Summary

Modifier and Type	Method and Description
double	getL1ByParam(String paramName) Get the L1 coefficient for the given parameter.
double	getL2ByParam(String paramName) Get the L2 coefficient for the given parameter.
double	getLearningRateByParam(String paramName) Get the (initial) learning rate coefficient for the given parameter.

Methods inherited from class org.deeplearning4j.nn.conf.layers.BaseRecurrentLayer

getOutputType, getPreProcessorForInputType, setNIn

Methods inherited from class org.deeplearning4j.nn.conf.layers.FeedForwardLayer

isPretrainParam

Methods inherited from class org.deeplearning4j.nn.conf.layers.BaseLayer

clone, getIUpdaterByParam, getUpdaterByParam, resetLayerDefaultConfig

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

getMemoryReport, initializer, instantiate

Methods inherited from class java.lang.Object

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

Field Detail

forgetGateBiasInit

protected double forgetGateBiasInit

gateActivationFn

protected org.nd4j.linalg.activations.IActivation gateActivationFn

Constructor Detail

AbstractLSTM

protected AbstractLSTM(AbstractLSTM.Builder builder)

Method Detail

getL1ByParam

public double getL1ByParam(String paramName)

Description copied from class: Layer

Get the L1 coefficient for the given parameter. Different parameters may have different L1 values, even for a single .l1(x) configuration. For example, biases generally aren't L1 regularized, even if weights are

Overrides:

getL1ByParam in class FeedForwardLayer

Parameters:

paramName - Parameter name

Returns:

L1 value for that parameter

getL2ByParam

public double getL2ByParam(String paramName)

Description copied from class: Layer

Get the L2 coefficient for the given parameter. Different parameters may have different L2 values, even for a single .l2(x) configuration. For example, biases generally aren't L1 regularized, even if weights are

Overrides:

getL2ByParam in class FeedForwardLayer

Parameters:

paramName - Parameter name

Returns:

L2 value for that parameter

getLearningRateByParam

public double getLearningRateByParam(String paramName)

Description copied from class: Layer

Get the (initial) learning rate coefficient for the given parameter. Different parameters may be configured to have different learning rates, though commonly all parameters will have the same learning rate

Overrides:

getLearningRateByParam in class FeedForwardLayer

Parameters:

paramName - Parameter name

Returns:

Initial learning rate value for that parameter