Built-In Layers

Build deep neural networks using built-in layers

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 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.

Apps

Deep Network Designer

Design and visualize deep learning networks

Functions

expand all

Built-In Layers

Input Layers

`inputLayer`	Input layer (Since R2023b)
`imageInputLayer`	Image input layer
`image3dInputLayer`	3-D image input layer
`sequenceInputLayer`	Sequence input layer
`featureInputLayer`	Feature input layer (Since R2020b)

Convolution and Fully Connected Layers

`convolution1dLayer`	1-D convolutional layer (Since R2021b)
`convolution2dLayer`	2-D convolutional layer
`convolution3dLayer`	3-D convolutional layer
`groupedConvolution2dLayer`	2-D grouped convolutional layer
`transposedConv1dLayer`	Transposed 1-D convolution layer (Since R2022a)
`transposedConv2dLayer`	Transposed 2-D convolution layer
`transposedConv3dLayer`	Transposed 3-D convolution layer
`fullyConnectedLayer`	Fully connected layer

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)
`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)
`attentionLayer`	Dot-product attention layer (Since R2024a)
`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)
`deep.ode.options.ODE1`	Neural ODE solver options for nonstiff differential equations using Euler method (Since R2025a)
`deep.ode.options.ODE45`	Neural ODE solver options for nonstiff differential equations (Since R2025a)

Activation Layers

`reluLayer`	Rectified Linear Unit (ReLU) layer
`leakyReluLayer`	Leaky Rectified Linear Unit (ReLU) layer
`preluLayer`	Parametrized Rectified Linear Unit (PReLU) layer (Since R2024a)
`clippedReluLayer`	Clipped Rectified Linear Unit (ReLU) layer
`eluLayer`	Exponential linear unit (ELU) layer
`tanhLayer`	Hyperbolic tangent (tanh) layer
`swishLayer`	Swish layer (Since R2021a)
`geluLayer`	Gaussian error linear unit (GELU) layer (Since R2022b)
`softmaxLayer`	Softmax layer
`sigmoidLayer`	Sigmoid layer (Since R2020b)
`softplusLayer`	Softplus layer
`complexReluLayer`	Complex rectified linear unit (ReLU) layer (Since R2025a)
`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

Utility Layers

`dropoutLayer`	Dropout layer
`spatialDropoutLayer`	Spatial dropout layer (Since R2024a)
`flattenLayer`	Flatten layer
`crop2dLayer`	2-D crop layer
`crop3dLayer`	3-D crop layer
`scalingLayer`	Scaling layer
`quadraticLayer`	Quadratic layer
`identityLayer`	Identity layer (Since R2024b)
`complexToRealLayer`	Complex-to-real layer (Since R2024b)
`realToComplexLayer`	Real-to-complex layer (Since R2024b)
`networkLayer`	Network Layer (Since R2024a)
`reshapeLayer`	Reshape layer (Since R2025a)
`permuteLayer`	Permute layer (Since R2025a)

Pooling and Unpooling Layers

`averagePooling1dLayer`	1-D average pooling layer (Since R2021b)
`averagePooling2dLayer`	Average pooling layer
`averagePooling3dLayer`	3-D average pooling layer
`adaptiveAveragePooling2dLayer`	Adaptive average pooling 2-D layer (Since R2024a)
`globalAveragePooling1dLayer`	1-D global average pooling layer (Since R2021b)
`globalAveragePooling2dLayer`	2-D global average pooling layer
`globalAveragePooling3dLayer`	3-D global average pooling layer
`globalMaxPooling1dLayer`	1-D global max pooling layer (Since R2021b)
`globalMaxPooling2dLayer`	Global max pooling layer
`globalMaxPooling3dLayer`	3-D global max pooling layer
`maxPooling1dLayer`	1-D max pooling layer (Since R2021b)
`maxPooling2dLayer`	Max pooling layer
`maxPooling3dLayer`	3-D max pooling layer
`maxUnpooling2dLayer`	Max unpooling layer

Combination Layers

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

Network Creation

`dlnetwork`	Deep learning neural network
`imagePretrainedNetwork`	Pretrained neural network for images (Since R2024a)
`resnetNetwork`	2-D residual neural network (Since R2024a)
`resnet3dNetwork`	3-D residual neural network (Since R2024a)
`dag2dlnetwork`	Convert `SeriesNetwork` and `DAGNetwork` to `dlnetwork` (Since R2024a)

Network Editing

`addLayers`	Add layers to neural network
`removeLayers`	Remove layers from neural network
`replaceLayer`	Replace layer in neural network
`getLayer`	Look up a layer by name or path (Since R2024a)
`connectLayers`	Connect layers in neural network
`disconnectLayers`	Disconnect layers in neural network
`expandLayers`	Expand network layers (Since R2024a)
`groupLayers`	Group layers into network layers (Since R2024a)
`addInputLayer`	Add input layer to network (Since R2022b)

Learnable Parameters

`initialize`	Initialize learnable and state parameters of neural network (Since R2021a)
`networkDataLayout`	Deep learning network data layout for learnable parameter initialization (Since R2022b)
`setL2Factor`	Set L₂ regularization factor of layer learnable parameter
`getL2Factor`	Get L₂ regularization factor of layer learnable parameter
`setLearnRateFactor`	Set learn rate factor of layer learnable parameter
`getLearnRateFactor`	Get learn rate factor of layer learnable parameter

Network Information

`plot`	Plot neural network architecture
`summary`	Print network summary (Since R2022b)
`analyzeNetwork`	Analyze deep learning network architecture
`checkLayer`	Check validity of custom or function layer
`isequal`	Check equality of neural networks (Since R2021a)
`isequaln`	Check equality of neural networks ignoring `NaN` values (Since R2021a)

Topics

Long Short-Term Memory Neural Networks
Learn about long short-term memory (LSTM) neural networks.
Create Simple Deep Learning Neural Network for Classification
This example shows how to create and train a simple convolutional neural network for deep learning classification.
Train Convolutional Neural Network for Regression
This example shows how to train a convolutional neural network to predict the angles of rotation of handwritten digits.
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.
Create and Train Network with Nested Layers
This example shows how to create and train a network with nested layers using network layers. (Since R2024a)
Example Deep Learning Networks Architectures
This example shows how to define simple deep learning neural networks for classification and regression tasks.
Choose an AI Model
Explore options for choosing an AI model.
Generate MATLAB Code from Deep Network Designer
Generate MATLAB code to recreate designing a network in Deep Network Designer.
Multiple-Input and Multiple-Output Networks
Learn how to define and train deep learning networks with multiple inputs or multiple outputs.

Featured Examples

Sequence Classification Using Deep Learning

Classify sequence data using a long short-term memory (LSTM) network.

Open Live Script

Convert Classification Network into Regression Network

Convert a trained classification network into a regression network.

Open Live Script

Sequence Classification Using 1-D Convolutions

Classify sequence data using a 1-D convolutional neural network.

Open Live Script

Build Image-to-Image Regression Network Using Deep Network Designer

Use Deep Network Designer to construct an image-to-image regression network for super resolution.

Open Live Script

Multilabel Image Classification Using Deep Learning

Use transfer learning to train a deep learning model for multilabel image classification.

Open Live Script

Get Started with Deep Network Designer

Create a simple recurrent neural network for deep learning sequence classification using Deep Network Designer.

Open Live Script

Get Started with Image Classification

Create a simple convolutional neural network for deep learning classification using the Deep Network Designer app. Convolutional neural networks are essential tools for deep learning and are especially suited for image recognition.

Open Live Script

Train Residual Network for Image Classification

Create a deep learning neural network with residual connections and train it on CIFAR-10 data. Residual connections are a popular element in convolutional neural network architectures. Using residual connections improves gradient flow through the network and enables training of deeper networks.

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

New

Interpretable Time Series Forecasting Using a Temporal Fusion Transformer

Forecast electricity usage using an interpretable temporal fusion transformer (TFT).

Since R2025a
Open Live Script

How useful was this information?

Unrated 1 star 2 stars 3 stars 4 stars 5 stars