Main Content


Addition layer


An addition layer adds inputs from multiple neural network layers element-wise.

Specify the number of inputs to the layer when you create it. The inputs to the layer have the names 'in1','in2',...,'inN', where N is the number of inputs. Use the input names when connecting or disconnecting the layer by using connectLayers or disconnectLayers. All inputs to an addition layer must have the same dimension.




layer = additionLayer(numInputs) creates an addition layer that adds numInputs inputs element-wise. This function also sets the NumInputs property.


layer = additionLayer(numInputs,'Name',Name) also sets the Name property. To create a network containing an addition layer, you must specify a layer name.


expand all

Number of inputs to the layer, specified as a positive integer.

The inputs have the names 'in1','in2',...,'inN', where N equals NumInputs. For example, if NumInputs equals 3, then the inputs have the names 'in1','in2', and 'in3'. Use the input names when connecting or disconnecting the layer by using connectLayers or disconnectLayers.

Layer name, specified as a character vector or a string scalar. To include this layer in a layer graph, you must specify a layer name.

Data Types: char | string

Input names, specified as {'in1','in2',...,'inN'}, where N is the number of inputs of the layer.

Data Types: cell

Number of outputs of the layer. This layer has a single output only.

Data Types: double

Output names of the layer. This layer has a single output only.

Data Types: cell


collapse all

Create an addition layer with two inputs and the name 'add_1'.

add = additionLayer(2,'Name','add_1')
add = 
  AdditionLayer with properties:

          Name: 'add_1'
     NumInputs: 2
    InputNames: {'in1'  'in2'}

Create two ReLU layers and connect them to the addition layer. The addition layer sums the outputs from the ReLU layers.

relu_1 = reluLayer('Name','relu_1');
relu_2 = reluLayer('Name','relu_2');

lgraph = layerGraph;
lgraph = addLayers(lgraph,relu_1);
lgraph = addLayers(lgraph,relu_2);
lgraph = addLayers(lgraph,add);

lgraph = connectLayers(lgraph,'relu_1','add_1/in1');
lgraph = connectLayers(lgraph,'relu_2','add_1/in2');


Figure contains an axes. The axes contains an object of type graphplot.

Create a simple directed acyclic graph (DAG) network for deep learning. Train the network to classify images of digits. The simple network in this example consists of:

  • A main branch with layers connected sequentially.

  • A shortcut connection containing a single 1-by-1 convolutional layer. Shortcut connections enable the parameter gradients to flow more easily from the output layer to the earlier layers of the network.

Create the main branch of the network as a layer array. The addition layer sums multiple inputs element-wise. Specify the number of inputs for the addition layer to sum. All layers must have names and all names must be unique.

layers = [
    imageInputLayer([28 28 1],'Name','input')

Create a layer graph from the layer array. layerGraph connects all the layers in layers sequentially. Plot the layer graph.

lgraph = layerGraph(layers);

Create the 1-by-1 convolutional layer and add it to the layer graph. Specify the number of convolutional filters and the stride so that the activation size matches the activation size of the 'relu_3' layer. This arrangement enables the addition layer to add the outputs of the 'skipConv' and 'relu_3' layers. To check that the layer is in the graph, plot the layer graph.

skipConv = convolution2dLayer(1,32,'Stride',2,'Name','skipConv');
lgraph = addLayers(lgraph,skipConv);

Create the shortcut connection from the 'relu_1' layer to the 'add' layer. Because you specified two as the number of inputs to the addition layer when you created it, the layer has two inputs named 'in1' and 'in2'. The 'relu_3' layer is already connected to the 'in1' input. Connect the 'relu_1' layer to the 'skipConv' layer and the 'skipConv' layer to the 'in2' input of the 'add' layer. The addition layer now sums the outputs of the 'relu_3' and 'skipConv' layers. To check that the layers are connected correctly, plot the layer graph.

lgraph = connectLayers(lgraph,'relu_1','skipConv');
lgraph = connectLayers(lgraph,'skipConv','add/in2');

Load the training and validation data, which consists of 28-by-28 grayscale images of digits.

[XTrain,YTrain] = digitTrain4DArrayData;
[XValidation,YValidation] = digitTest4DArrayData;

Specify training options and train the network. trainNetwork validates the network using the validation data every ValidationFrequency iterations.

options = trainingOptions('sgdm', ...
    'MaxEpochs',8, ...
    'Shuffle','every-epoch', ...
    'ValidationData',{XValidation,YValidation}, ...
    'ValidationFrequency',30, ...
    'Verbose',false, ...
net = trainNetwork(XTrain,YTrain,lgraph,options);

Display the properties of the trained network. The network is a DAGNetwork object.

net = 
  DAGNetwork with properties:

         Layers: [16×1 nnet.cnn.layer.Layer]
    Connections: [16×2 table]
     InputNames: {'input'}
    OutputNames: {'classOutput'}

Classify the validation images and calculate the accuracy. The network is very accurate.

YPredicted = classify(net,XValidation);
accuracy = mean(YPredicted == YValidation)
accuracy = 0.9930

Extended Capabilities

C/C++ Code Generation
Generate C and C++ code using MATLAB® Coder™.

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

Introduced in R2017b