org.deeplearning4j.nn.layers.feedforward.embedding

Class EmbeddingLayer

java.lang.Object

org.deeplearning4j.nn.layers.AbstractLayer<LayerConfT>

org.deeplearning4j.nn.layers.BaseLayer<EmbeddingLayer>

org.deeplearning4j.nn.layers.feedforward.embedding.EmbeddingLayer

All Implemented Interfaces:

Serializable, Cloneable, Layer, Model

public class EmbeddingLayer
extends BaseLayer<EmbeddingLayer>

Embedding layer: feed-forward layer that expects single integers per example as input (class numbers, in range 0 to numClass-1) as input. This input has shape [numExamples,1] instead of [numExamples,numClasses] for the equivalent one-hot representation. Mathematically, EmbeddingLayer is equivalent to using a DenseLayer with a one-hot representation for the input; however, it can be much more efficient with a large number of classes (as a dense layer + one-hot input does a matrix multiply with all but one value being zero).
Note: can only be used as the first layer for a network
Note 2: For a given example index i, the output is activationFunction(weights.getRow(i) + bias), hence the weight rows can be considered a vector/embedding for each example.

Author:

Alex Black

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from interface org.deeplearning4j.nn.api.Layer

Layer.TrainingMode, Layer.Type

Field Summary

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

gradient, gradientsFlattened, gradientViews, optimizer, params, paramsFlattened, score, solver, weightNoiseParams

Fields inherited from class org.deeplearning4j.nn.layers.AbstractLayer

cacheMode, conf, dropoutApplied, dropoutMask, epochCount, index, input, iterationCount, maskArray, maskState, preOutput, trainingListeners

Constructor Summary

Constructors

Constructor and Description
EmbeddingLayer(NeuralNetConfiguration conf)

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.api.ndarray.INDArray	activate(boolean training, LayerWorkspaceMgr workspaceMgr) Perform forward pass and return the activations array with the last set input
protected void	applyDropOutIfNecessary(boolean training, LayerWorkspaceMgr workspaceMgr)
org.nd4j.linalg.primitives.Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon, LayerWorkspaceMgr workspaceMgr) Calculate the gradient relative to the error in the next layer
boolean	hasBias() Does this layer have no bias term? Many layers (dense, convolutional, output, embedding) have biases by default, but no-bias versions are possible via configuration
boolean	isPretrainLayer() Returns true if the layer can be trained in an unsupervised/pretrain manner (AE, VAE, etc)
protected org.nd4j.linalg.api.ndarray.INDArray	preOutput(boolean training, LayerWorkspaceMgr workspaceMgr)

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

accumulateScore, calcL1, calcL2, clear, clearNoiseWeightParams, clone, computeGradientAndScore, fit, fit, getGradientsViewArray, getOptimizer, getParam, getParamWithNoise, gradient, initParams, layerConf, numParams, params, paramTable, paramTable, score, setBackpropGradientsViewArray, setParam, setParams, setParams, setParamsViewArray, setParamTable, setScoreWithZ, toString, transpose, update, update

Methods inherited from class org.deeplearning4j.nn.layers.AbstractLayer

activate, addListeners, applyConstraints, applyMask, assertInputSet, batchSize, conf, feedForwardMaskArray, getIndex, getInput, getInputMiniBatchSize, getListeners, getMaskArray, gradientAndScore, init, input, layerId, numParams, setCacheMode, setConf, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setMaskArray, type, validateInput

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.deeplearning4j.nn.api.Layer

getEpochCount, getIterationCount, setEpochCount, setIterationCount

Constructor Detail

EmbeddingLayer

public EmbeddingLayer(NeuralNetConfiguration conf)

Method Detail

backpropGradient

public org.nd4j.linalg.primitives.Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray> backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon,
                                                                                                       LayerWorkspaceMgr workspaceMgr)

Description copied from interface: Layer

Calculate the gradient relative to the error in the next layer

Specified by:

backpropGradient in interface Layer

Overrides:

backpropGradient in class BaseLayer<EmbeddingLayer>

Parameters:

epsilon - w^(L+1)*delta^(L+1). Or, equiv: dC/da, i.e., (dC/dz)*(dz/da) = dC/da, where C is cost function a=sigma(z) is activation.

workspaceMgr - Workspace manager

Returns:

Pair where Gradient is gradient for this layer, INDArray is epsilon (activation gradient) needed by next layer, but before element-wise multiply by sigmaPrime(z). So for standard feed-forward layer, if this layer is L, then return.getSecond() == dL/dIn = (w^(L)*(delta^(L))^T)^T. Note that the returned array should be placed in the ArrayType.ACTIVATION_GRAD workspace via the workspace manager

preOutput

protected org.nd4j.linalg.api.ndarray.INDArray preOutput(boolean training,
                                                         LayerWorkspaceMgr workspaceMgr)

Overrides:

preOutput in class BaseLayer<EmbeddingLayer>

activate

public org.nd4j.linalg.api.ndarray.INDArray activate(boolean training,
                                                     LayerWorkspaceMgr workspaceMgr)

Description copied from interface: Layer

Perform forward pass and return the activations array with the last set input

Specified by:

activate in interface Layer

Overrides:

activate in class BaseLayer<EmbeddingLayer>

Parameters:

training - training or test mode

workspaceMgr - Workspace manager

Returns:

the activation (layer output) of the last specified input. Note that the returned array should be placed in the ArrayType.ACTIVATIONS workspace via the workspace manager

hasBias

public boolean hasBias()

Description copied from class: BaseLayer

Does this layer have no bias term? Many layers (dense, convolutional, output, embedding) have biases by default, but no-bias versions are possible via configuration

Overrides:

hasBias in class BaseLayer<EmbeddingLayer>

Returns:

True if a bias term is present, false otherwise

isPretrainLayer

public boolean isPretrainLayer()

Description copied from interface: Layer

Returns true if the layer can be trained in an unsupervised/pretrain manner (AE, VAE, etc)

Returns:

true if the layer can be pretrained (using fit(INDArray), false otherwise

applyDropOutIfNecessary

protected void applyDropOutIfNecessary(boolean training,
                                       LayerWorkspaceMgr workspaceMgr)

Overrides:

applyDropOutIfNecessary in class AbstractLayer<EmbeddingLayer>