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.

Apps

Deep Network Designer

Design, visualize, and train deep learning networks

Functions

expand all

Built-In Layers

Input Layers

`sequenceInputLayer`	Sequence input layer
`featureInputLayer`	Feature input layer (Since R2020b)

Recurrent Layers

`lstmLayer`	Long short-term memory (LSTM) layer for recurrent neural network (RNN)
`bilstmLayer`	Bidirectional long short-term memory (BiLSTM) layer for recurrent neural network (RNN)
`gruLayer`	Gated recurrent unit (GRU) layer for recurrent neural network (RNN) (Since R2020a)
`lstmProjectedLayer`	Long short-term memory (LSTM) projected layer for recurrent neural network (RNN) (Since R2022b)
`gruProjectedLayer`	Gated recurrent unit (GRU) projected layer for recurrent neural network (RNN) (Since R2023b)

Transformer Layers

`selfAttentionLayer`	Self-attention layer (Since R2023a)
`positionEmbeddingLayer`	Position embedding layer (Since R2023b)
`sinusoidalPositionEncodingLayer`	Sinusoidal position encoding layer (Since R2023b)
`embeddingConcatenationLayer`	Embedding concatenation layer (Since R2023b)
`indexing1dLayer`	1-D indexing layer (Since R2023b)

Neural ODE Layers

neuralODELayer Neural ODE layer (Since R2023b)

Convolution, Attention, and Fully Connected Layers

`convolution1dLayer`	1-D convolutional layer (Since R2021b)
`transposedConv1dLayer`	Transposed 1-D convolution layer (Since R2022a)
`selfAttentionLayer`	Self-attention layer (Since R2023a)
`fullyConnectedLayer`	Fully connected layer

Activation and Dropout Layers

`reluLayer`	Rectified Linear Unit (ReLU) layer
`leakyReluLayer`	Leaky Rectified Linear Unit (ReLU) layer
`clippedReluLayer`	Clipped Rectified Linear Unit (ReLU) layer
`eluLayer`	Exponential linear unit (ELU) layer (Since R2019a)
`tanhLayer`	Hyperbolic tangent (tanh) layer (Since R2019a)
`swishLayer`	Swish layer (Since R2021a)
`geluLayer`	Gaussian error linear unit (GELU) layer (Since R2022b)
`sigmoidLayer`	Sigmoid layer (Since R2020b)
`softmaxLayer`	Softmax layer
`dropoutLayer`	Dropout layer
`functionLayer`	Function layer (Since R2021b)

Normalization Layers

`batchNormalizationLayer`	Batch normalization layer
`groupNormalizationLayer`	Group normalization layer (Since R2020b)
`instanceNormalizationLayer`	Instance normalization layer (Since R2021a)
`layerNormalizationLayer`	Layer normalization layer (Since R2021a)
`crossChannelNormalizationLayer`	Channel-wise local response normalization layer

Pooling Layers

`maxPooling1dLayer`	1-D max pooling layer (Since R2021b)
`averagePooling1dLayer`	1-D average pooling layer (Since R2021b)
`globalMaxPooling1dLayer`	1-D global max pooling layer (Since R2021b)
`globalAveragePooling1dLayer`	1-D global average pooling layer (Since R2021b)

Combination Layers

`additionLayer`	Addition layer
`multiplicationLayer`	Multiplication layer (Since R2020b)
`concatenationLayer`	Concatenation layer (Since R2019a)
`depthConcatenationLayer`	Depth concatenation layer

Data Manipulation

`sequenceFoldingLayer`	Sequence folding layer (Since R2019a)
`sequenceUnfoldingLayer`	Sequence unfolding layer (Since R2019a)
`flattenLayer`	Flatten layer (Since R2019a)

Output Layers

`classificationLayer`	Classification output layer
`regressionLayer`	Regression output layer

Build Network

`layerGraph`	Graph of network layers for deep learning
`plot`	Plot neural network architecture
`addLayers`	Add layers to layer graph or network
`removeLayers`	Remove layers from layer graph or network
`replaceLayer`	Replace layer in layer graph or network
`connectLayers`	Connect layers in layer graph or network
`disconnectLayers`	Disconnect layers in layer graph or network
`DAGNetwork`	Directed acyclic graph (DAG) network for deep learning
`isequal`	Check equality of deep learning layer graphs or networks (Since R2021a)
`isequaln`	Check equality of deep learning layer graphs or networks ignoring `NaN` values (Since R2021a)
`analyzeNetwork`	Analyze deep learning network architecture

Custom Networks

`dlnetwork`	Deep learning network for custom training loops (Since R2019b)
`addInputLayer`	Add input layer to network (Since R2022b)
`summary`	Print network summary (Since R2022b)
`initialize`	Initialize learnable and state parameters of a `dlnetwork` (Since R2021a)
`networkDataLayout`	Deep learning network data layout for learnable parameter initialization (Since R2022b)
`checkLayer`	Check validity of custom or function layer

Topics

Built-In Layers

Train Network with Numeric Features
This example shows how to create and train a simple neural network for deep learning feature data classification.
Create Simple Sequence Classification Network Using Deep Network Designer
This example shows how to create a simple long short-term memory (LSTM) classification network using Deep Network Designer.
Sequence Classification Using Deep Learning
This example shows how to classify sequence data using a long short-term memory (LSTM) network.
Sequence-to-Sequence Classification Using Deep Learning
This example shows how to classify each time step of sequence data using a long short-term memory (LSTM) network.
Sequence-to-Sequence Regression Using Deep Learning
This example shows how to predict the remaining useful life (RUL) of engines by using deep learning.
Sequence-to-One Regression Using Deep Learning
This example shows how to predict the frequency of a waveform using a long short-term memory (LSTM) neural network.
Long Short-Term Memory Neural Networks
Learn about long short-term memory (LSTM) neural networks.
Example Deep Learning Networks Architectures
This example shows how to define simple deep learning neural networks for classification and regression tasks.
Multiple-Input and Multiple-Output Networks
Learn how to define and train deep learning networks with multiple inputs or multiple outputs.
List of Deep Learning Layers
Discover all the deep learning layers in MATLAB.
Build Networks with Deep Network Designer
Interactively build and edit deep learning networks in Deep Network Designer.
Deep Learning in MATLAB
Discover deep learning capabilities in MATLAB using convolutional neural networks for classification and regression, including pretrained networks and transfer learning, and training on GPUs, CPUs, clusters, and clouds.
Deep Learning Tips and Tricks
Learn how to improve the accuracy of deep learning networks.
Data Sets for Deep Learning
Discover data sets for various deep learning tasks.

Custom Layers

Define Custom Deep Learning Layers
Learn how to define custom deep learning layers.
Define Custom Deep Learning Intermediate Layers
Learn how to define custom deep learning intermediate layers.
Define Custom Deep Learning Output Layers
Learn how to define custom deep learning output layers.
Check Custom Layer Validity
Learn how to check the validity of custom deep learning layers.
Replace Unsupported Keras Layer with Function Layer
This example shows how to import the layers from a pretrained Keras network, replace the unsupported layers with function layers, and assemble the layers into a network ready for prediction.

Featured Examples

Time Series Forecasting Using Deep Learning

Forecast time series data using a long short-term memory (LSTM) network.

Open Live Script

Train Speech Command Recognition Model Using Deep Learning

Train a deep learning model that detects the presence of speech commands in audio. The example uses the Speech Commands Dataset [1] to train a convolutional neural network to recognize a set of commands.

Open Live Script

Chemical Process Fault Detection Using Deep Learning

Use simulation data to train a neural network than can detect faults in a chemical process.

Open Live Script

Train Network on Image and Feature Data

Train a network that classifies handwritten digits using both image and feature input data.

Open Live Script

Predict Battery State of Charge Using Deep Learning

Train a neural network to predict the state of charge of a battery by using deep learning.

Open Live Script