Main Content

Build Deep Neural Networks

Build networks for sequence and tabular data using MATLAB® code or interactively using Deep Network Designer

Create new deep networks for tasks such as classification, regression, and forecasting by defining the network architecture from scratch. Build networks using MATLAB or interactively using Deep Network Designer.

For most tasks, you can use built-in layers. If there is not a built-in layer that you need for your task, then you can define your own custom layer. You can specify a custom loss function using a custom output layer and define custom layers with learnable and state parameters. After defining a custom layer, you can check that the layer is valid, GPU compatible, and outputs correctly defined gradients. For a list of supported layers, see List of Deep Learning Layers.

For models that layer graphs do not support, you can define a custom model as a function. To learn more, see Define Custom Training Loops, Loss Functions, and Networks.


Deep Network DesignerDesign, visualize, and train deep learning networks


expand all

Input Layers

sequenceInputLayerSequence input layer
featureInputLayerFeature input layer (Since R2020b)

Recurrent Layers

lstmLayerLong short-term memory (LSTM) layer for recurrent neural network (RNN)
bilstmLayerBidirectional long short-term memory (BiLSTM) layer for recurrent neural network (RNN)
gruLayerGated recurrent unit (GRU) layer for recurrent neural network (RNN) (Since R2020a)
lstmProjectedLayerLong short-term memory (LSTM) projected layer for recurrent neural network (RNN) (Since R2022b)
gruProjectedLayerGated recurrent unit (GRU) projected layer for recurrent neural network (RNN) (Since R2023b)

Transformer Layers

selfAttentionLayerSelf-attention layer (Since R2023a)
positionEmbeddingLayerPosition embedding layer (Since R2023b)
sinusoidalPositionEncodingLayerSinusoidal position encoding layer (Since R2023b)
embeddingConcatenationLayerEmbedding concatenation layer (Since R2023b)
indexing1dLayer1-D indexing layer (Since R2023b)

Neural ODE Layers

neuralODELayerNeural ODE layer (Since R2023b)

Convolution, Attention, and Fully Connected Layers

convolution1dLayer1-D convolutional layer (Since R2021b)
transposedConv1dLayerTransposed 1-D convolution layer (Since R2022a)
selfAttentionLayerSelf-attention layer (Since R2023a)
fullyConnectedLayerFully connected layer

Activation and Dropout Layers

reluLayerRectified Linear Unit (ReLU) layer
leakyReluLayerLeaky Rectified Linear Unit (ReLU) layer
clippedReluLayerClipped Rectified Linear Unit (ReLU) layer
eluLayerExponential linear unit (ELU) layer (Since R2019a)
tanhLayerHyperbolic tangent (tanh) layer (Since R2019a)
swishLayerSwish layer (Since R2021a)
geluLayerGaussian error linear unit (GELU) layer (Since R2022b)
sigmoidLayerSigmoid layer (Since R2020b)
softmaxLayerSoftmax layer
dropoutLayerDropout layer
functionLayerFunction layer (Since R2021b)

Normalization Layers

batchNormalizationLayerBatch normalization layer
groupNormalizationLayerGroup normalization layer (Since R2020b)
instanceNormalizationLayerInstance normalization layer (Since R2021a)
layerNormalizationLayerLayer normalization layer (Since R2021a)
crossChannelNormalizationLayer Channel-wise local response normalization layer

Pooling Layers

maxPooling1dLayer1-D max pooling layer (Since R2021b)
averagePooling1dLayer1-D average pooling layer (Since R2021b)
globalMaxPooling1dLayer1-D global max pooling layer (Since R2021b)
globalAveragePooling1dLayer1-D global average pooling layer (Since R2021b)

Combination Layers

additionLayerAddition layer
multiplicationLayerMultiplication layer (Since R2020b)
concatenationLayerConcatenation layer (Since R2019a)
depthConcatenationLayerDepth concatenation layer

Data Manipulation

sequenceFoldingLayerSequence folding layer (Since R2019a)
sequenceUnfoldingLayerSequence unfolding layer (Since R2019a)
flattenLayerFlatten layer (Since R2019a)

Output Layers

classificationLayerClassification output layer
regressionLayerRegression output layer
layerGraphGraph of network layers for deep learning
plotPlot neural network architecture
addLayersAdd layers to layer graph or network
removeLayersRemove layers from layer graph or network
replaceLayerReplace layer in layer graph or network
connectLayersConnect layers in layer graph or network
disconnectLayersDisconnect layers in layer graph or network
DAGNetworkDirected acyclic graph (DAG) network for deep learning
isequalCheck equality of deep learning layer graphs or networks (Since R2021a)
isequalnCheck equality of deep learning layer graphs or networks ignoring NaN values (Since R2021a)
analyzeNetworkAnalyze deep learning network architecture
dlnetworkDeep learning network for custom training loops (Since R2019b)
addInputLayerAdd input layer to network (Since R2022b)
summaryPrint network summary (Since R2022b)
initializeInitialize learnable and state parameters of a dlnetwork (Since R2021a)
networkDataLayoutDeep learning network data layout for learnable parameter initialization (Since R2022b)
checkLayerCheck validity of custom or function layer


Built-In Layers

Custom Layers