Class EmbeddingLayer

Namespace

NeuralNetworks.Layers

Assembly

NeuralNetworks.dll

Embedding layer that maps integer indices to dense vectors. Used in Word2Vec and other NLP models.

public class EmbeddingLayer : Layer<int[,], float[,]>

Inheritance

object

Layer

Layer<int[,], float[,]>

EmbeddingLayer

Inherited Members

Layer<int[,], float[,]>.Input

Layer<int[,], float[,]>.Output

Layer<int[,], float[,]>.Forward(int[,], bool)

Layer<int[,], float[,]>.Backward(float[,])

Layer<int[,], float[,]>.UpdateParams(Optimizer)

Layer<int[,], float[,]>.CreateOperationListBuilder()

Layer<int[,], float[,]>.SetupLayer()

Layer<int[,], float[,]>.AddOperation<TOpOut>(Operation<int[,], TOpOut>)

Layer<int[,], float[,]>.GetOutputType()

Layer<int[,], float[,]>.GetInputType()

Layer<int[,], float[,]>.Forward(object, bool)

Layer<int[,], float[,]>.Backward(object)

Layer<int[,], float[,]>.GetParamCount()

Layer.SetRegistered()

Layer.GetOutputType()

Layer.GetInputType()

Layer.Forward(object, bool)

Layer.Backward(object)

Layer.UpdateParams(Optimizer)

Layer.GetParamCount()

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

Remarks

Initializes a new instance of the EmbeddingLayer class.

Constructors

EmbeddingLayer(int, int, ParamInitializer)

Embedding layer that maps integer indices to dense vectors. Used in Word2Vec and other NLP models.

public EmbeddingLayer(int vocabSize, int embeddingDim, ParamInitializer paramInitializer)

Parameters

vocabSize int

Size of the vocabulary (number of unique tokens).

embeddingDim int

Dimensionality of the embedding vectors.

paramInitializer ParamInitializer

Initializer for embedding weights.

Remarks

Initializes a new instance of the EmbeddingLayer class.

Methods

CreateOperationListBuilder()

public override OperationListBuilder<int[,], float[,]> CreateOperationListBuilder()

Returns

OperationListBuilder<int[,], float[,]>

GetEmbeddings()

Gets parameters from the EmbeddingLookup operation.

public float[,] GetEmbeddings()

Returns

float[,]

Embedding matrix [vocabSize, embeddingDim].

ToString()

Returns a string that represents the current object.

public override string ToString()

Returns

string

A string that represents the current object.