embeddingConcatenationLayer

Embedding concatenation layer

Since R2023b

Description

An embedding concatenation layer combines its input and an embedding vector by concatenation.

Creation

Syntax

layer = embeddingConcatenationLayer

layer = embeddingConcatenationLayer(Name=Value)

Description

layer = embeddingConcatenationLayer creates an embedding concatenation layer.

layer = embeddingConcatenationLayer(Name=Value) creates an embedding concatenation layer and sets the Parameters and Initialization and Name properties using one or more name-value arguments.

Properties

Parameters and Initialization

WeightsInitializer — Function to initialize weights

"narrow-normal" (default) | "glorot" | "he" | "zeros" | "ones" | function handle

Function to initialize the weights, specified as one of these values:

• "narrow-normal" — Initialize the weights by independently sampling from a normal distribution with zero mean and a standard deviation of 0.01.

• "glorot" — Initialize the weights with the Glorot initializer [1] (also known as Xavier initializer). The Glorot initializer independently samples from a uniform distribution with zero mean and a variance of 2/(numIn + numOut), where numIn and numOut are the number of channels in the layer input, respectively.

• "he" — Initialize the weights with the He initializer [2]. The He initializer samples from a normal distribution with zero mean and a variance of 2/numIn, where numIn is the number of channels in the layer input.

• "zeros" — Initialize the weights with zeros.

• "ones" — Initialize the weights with ones.

• Function handle – Initialize the weights with a custom function. If you specify a function handle, then the function must have the form weights = func(sz), where sz is the size of the weights.

The layer initializes the weights only when the Weights property is empty.

Weights — Learnable weights

[] (default) | column vector

Learnable weights, specified as a numeric column vector of length numChannels or [].

The layer weights are learnable parameters. You can specify the initial value of the weights directly using the Weights property of the layer. When you train a network, if the Weights property of the layer is nonempty, then the trainnet and trainNetwork functions use the Weights property as the initial value. If the Weights property is empty, then the software uses the initializer specified by the WeightsInitializer property of the layer.

Data Types: single | double

Layer

Name — Layer name

"" (default) | character vector | string scalar

Layer name, specified as a character vector or a string scalar. For Layer array input, the trainnet and dlnetwork functions automatically assign names to layers with the name "".

The EmbeddingConcatenationLayer object stores this property as a character vector.

Data Types: char | string

NumInputs — Number of inputs

1 (default)

This property is read-only.

Number of inputs to the layer, returned as 1. This layer accepts a single input only.

Data Types: double

InputNames — Input names

{'in'} (default)

This property is read-only.

Input names, returned as {'in'}. This layer accepts a single input only.

Data Types: cell

NumOutputs — Number of outputs

1 (default)

This property is read-only.

Number of outputs from the layer, returned as 1. This layer has a single output only.

Data Types: double

OutputNames — Output names

{'out'} (default)

This property is read-only.

Output names, returned as {'out'}. This layer has a single output only.

Data Types: cell

Examples

Create Embedding Concatenation Layer

Create an embedding concatenation layer.

layer = embeddingConcatenationLayer

layer = 
  EmbeddingConcatenationLayer with properties:

                     Name: ''
                InputSize: 'auto'
       WeightsInitializer: 'narrow-normal'
    WeightLearnRateFactor: 1
           WeightL2Factor: 1

   Learnable Parameters
                  Weights: []

   State Parameters
    No properties.

Use properties method to see a list of all properties.

Include an embedding concatenation layer in a neural network.

net = dlnetwork;

numChannels = 1;

embeddingOutputSize = 64;
numWords = 128;

maxSequenceLength = 100;
maxPosition = maxSequenceLength+1;

numHeads = 4;
numKeyChannels = 4*embeddingOutputSize;

layers = [ 
    sequenceInputLayer(numChannels)
    wordEmbeddingLayer(embeddingOutputSize,numWords,Name="word-emb")
    embeddingConcatenationLayer(Name="emb-cat")
    positionEmbeddingLayer(embeddingOutputSize,maxPosition,Name="pos-emb");
    additionLayer(2,Name="add")
    selfAttentionLayer(numHeads,numKeyChannels,AttentionMask="causal")
    fullyConnectedLayer(numWords)
    softmaxLayer];
net = addLayers(net,layers);

net = connectLayers(net,"emb-cat","add/in2");

View the neural network architecture.

plot(net)
axis off
box off

Algorithms

Embedding Concatenation Layer

An embedding concatenation layer combines its input and an embedding vector by concatenation.

The output of the layer has the same number of dimensions as the input. In the output, each vector in the first position over the channel dimension is the learnable embedding weights vector Weights.

For example:

• For sequence data X represented by a numChannels-by-numObservations-by-numTimeSteps array, where numChannels, numObservations, and numTimeSteps are the numbers of channels, observations, and time steps of the input, respectively, the output is an OutputSize-by-numObservations-by-(numTimeSteps+1) array Y, where Y(:,:,1) is Weights and Y(:,:,2:end) is X.

• For 1-D image data X represented by a height-by-numChannels-by-numObservations array, where height, numChannels, and numObservations are the height, number of channels, and the number of observations of the input images, respectively, the output is a (height+1)-by-OutputSize-by-numObservations array Y, where Y(1,:,:) is Weights and Y(2:end,:,:) is X.

Layer Input and Output Formats

Layers in a layer array or layer graph pass data to subsequent layers as formatted dlarray objects. The format of a dlarray object is a string of characters, in which each character describes the corresponding dimension of the data. The formats consist of one or more of these characters:

• "S" — Spatial

• "C" — Channel

• "B" — Batch

• "T" — Time

• "U" — Unspecified

For example, 2-D image data that is represented as a 4-D array, where the first two dimensions correspond to the spatial dimensions of the images, the third dimension corresponds to the channels of the images, and the fourth dimension corresponds to the batch dimension, can be described as having the format "SSCB" (spatial, spatial, channel, batch).

You can interact with these dlarray objects in automatic differentiation workflows, such as those for developing a custom layer, using a functionLayer object, or using the forward and predict functions with dlnetwork objects.

This table shows the supported input formats of EmbeddingConcatenationLayer objects and the corresponding output format. If the software passes the output of the layer to a custom layer that does not inherit from the nnet.layer.Formattable class, or a FunctionLayer object with the Formattable property set to 0 (false), then the layer receives an unformatted dlarray object with dimensions ordered according to the formats in this table. The formats listed here are only a subset. The layer may support additional formats such as formats with additional "S" (spatial) or "U" (unspecified) dimensions.

Input Format	Output Format
"SCB" (spatial, channel, batch)	"SCB" (spatial, channel, batch)
"CBT" (channel, batch, time)	"CBT" (channel, batch, time)
"SC" (spatial, channel)	"SC" (spatial, channel)

In dlnetwork objects, EmbeddingConcatenationLayer objects also support these input and output format combinations.

Input Format	Output Format
"CT" (channel, time)	"CT" (channel, time)

References

[1] Glorot, Xavier, and Yoshua Bengio. "Understanding the Difficulty of Training Deep Feedforward Neural Networks." In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 249–356. Sardinia, Italy: AISTATS, 2010. https://proceedings.mlr.press/v9/glorot10a/glorot10a.pdf

[2] He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. "Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification." In 2015 IEEE International Conference on Computer Vision (ICCV), 1026–34. Santiago, Chile: IEEE, 2015. https://doi.org/10.1109/ICCV.2015.123

Extended Capabilities

C/C++ Code Generation

Generate C and C++ code using MATLAB® Coder™.

Usage notes and limitations:

You can generate generic C/C++ code that does not depend on third-party libraries and deploy the generated code to hardware platforms.

GPU Code Generation

Generate CUDA® code for NVIDIA® GPUs using GPU Coder™.

Usage notes and limitations:

You can generate CUDA code that is independent of deep learning libraries and deploy the generated code to platforms that use NVIDIA^® or ARM^® GPU processors.

Version History

Introduced in R2023b