Main Content

Deep Learning with Simulink

Extend deep learning workflows using Simulink

Implement deep learning functionality in Simulink® models by using blocks from the Deep Neural Networks, Python Neural Networks, and Deep Learning Layers block libraries, included in the Deep Learning Toolbox™, or by using the Deep Learning Object Detector block from the Analysis & Enhancement block library included in the Computer Vision Toolbox™.

To generate a Simulink model that uses the Deep Learning Layers block library to represent a network, use the exportNetworkToSimulink function.

Some deep learning functionality in Simulink uses a MATLAB Function block that requires a supported compiler. For most platforms, a default C compiler is supplied with the MATLAB® installation. When using C++ language, you must install a compatible C++ compiler. To see a list of supported compilers, open Supported and Compatible Compilers, click the tab that corresponds to your operating system, find the Simulink Product Family table, and go to the For Model Referencing, Accelerator mode, Rapid Accelerator mode, and MATLAB Function blocks column. If you have multiple MATLAB-supported compilers installed on your system, you can change the default compiler using the mex -setup command. See Change Default Compiler.

Functions

exportNetworkToSimulinkGenerate Simulink model that contains deep learning layer blocks that correspond to deep learning layer objects (Since R2024b)

Blocks

expand all

Image ClassifierClassify data using a trained deep learning neural network (Since R2020b)
PredictPredict responses using a trained deep learning neural network (Since R2020b)
Stateful ClassifyClassify data using a trained deep learning recurrent neural network (Since R2021a)
Stateful PredictPredict responses using a trained recurrent neural network (Since R2021a)
Deep Learning Object DetectorDetect objects using trained deep learning object detector (Since R2021b)
TensorFlow Model PredictPredict responses using pretrained Python TensorFlow model (Since R2024a)
PyTorch Model PredictPredict responses using pretrained Python PyTorch model (Since R2024a)
ONNX Model PredictPredict responses using pretrained Python ONNX model (Since R2024a)
Custom Python Model PredictPredict responses using pretrained custom Python model (Since R2024a)
Clipped ReLU LayerClipped Rectified Linear Unit (ReLU) layer (Since R2024b)
GELU LayerGaussian error linear unit (GELU) layer (Since R2024b)
Leaky ReLU LayerLeaky rectified linear unit (ReLU) layer (Since R2024b)
ReLU LayerRectified linear unit (ReLU) layer (Since R2024b)
Sigmoid LayerSigmoid layer (Since R2024b)
Softmax LayerSoftmax layer (Since R2024b)
Tanh LayerHyperbolic tangent (tanh) layer (Since R2024a)
Addition LayerAddition layer (Since R2024b)
Concatenation LayerConcatenation layer (Since R2024b)
Depth Concatenation LayerDepth concatenation layer (Since R2024b)
Multiplication LayerMultiplication layer (Since R2024b)
Convolution 1D Layer1-D convolutional layer (Since R2024b)
Convolution 2D Layer2-D convolutional layer (Since R2024b)
Convolution 3D Layer3-D convolutional layer (Since R2024b)
Fully Connected LayerFully connected layer (Since R2024b)
Rescale-Symmetric 1D1-D input layer with rescale-symmetric normalization (Since R2024b)
Rescale-Symmetric 2D2-D input layer with rescale-symmetric normalization (Since R2024b)
Rescale-Symmetric 3D3-D input layer with rescale-symmetric normalization (Since R2024b)
Rescale-Zero-One 1D1-D input layer with rescale-zero-one normalization (Since R2024b)
Rescale-Zero-One 2D2-D input layer with rescale-zero-one normalization (Since R2024b)
Rescale-Zero-One 3D3-D input layer with rescale-zero-one normalization (Since R2024b)
Zerocenter 1D1-D input layer with zerocenter normalization (Since R2024b)
Zerocenter 2D2-D input layer with zerocenter normalization (Since R2024b)
Zerocenter 3D3-D input layer with zerocenter normalization (Since R2024b)
Zscore 1D1-D input layer with zscore normalization (Since R2024b)
Zscore 2D2-D input layer with zscore normalization (Since R2024b)
Zscore 3D3-D input layer with zscore normalization (Since R2024b)
Batch Normalization LayerBatch normalization layer (Since R2024b)
Layer Normalization LayerLayer normalization layer (Since R2024b)
Average Pooling 1D Layer1-D average pooling layer (Since R2024b)
Average Pooling 2D Layer2-D average pooling layer (Since R2024b)
Average Pooling 3D Layer3-D average pooling layer (Since R2024b)
Global Average Pooling 1D Layer1-D global average pooling layer (Since R2024b)
Global Average Pooling 2D Layer2-D global average pooling layer (Since R2024b)
Global Average Pooling 3D Layer3-D global average pooling layer (Since R2024b)
Global Max Pooling 1D Layer1-D global max pooling layer (Since R2024b)
Global Max Pooling 2D Layer2-D global max pooling layer (Since R2024b)
Global Max Pooling 3D Layer3-D global max pooling layer (Since R2024b)
Max Pooling 1D Layer1-D max pooling layer (Since R2024b)
Max Pooling 2D Layer2-D max pooling layer (Since R2024b)
Max Pooling 3D Layer3-D max pooling layer (Since R2024b)
Flatten LayerFlatten layer (Since R2024b)
LSTM LayerLong short-term memory (LSTM) layer for recurrent neural network (RNN) (Since R2024b)
LSTM Projected LayerLong short-term memory (LSTM) projected layer for recurrent neural network (RNN) (Since R2024b)
Dropout LayerDropout layer (Since R2024b)

Topics

Deep Learning Layer Blocks

Images

Sequences

Reinforcement Learning

Python Coexecution

Code Generation

Featured Examples