Deep Learning with Simulink
R2026bImplement 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. Blocks from the Deep
Learning Layers block library support code generation.
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.
By default, blocks from the Deep Neural Networks block library automatically use either code generation or interpreted execution based on model configuration and code generation support. When using interpreted execution, the block runs via the MATLAB execution engine and does not require a compiler. For more information, see Improve Performance of Deep Learning Simulations in Simulink.
Functions
exportNetworkToSimulink | Generate Simulink model that contains deep learning layer blocks and subsystems that correspond to deep learning layer objects (Since R2024b) |
Blocks
 | Classify | Classify data using a trained deep learning neural network |
 | Predict | Predict responses using a trained deep learning neural network |
 | Stateful Classify | Classify data using a trained deep learning recurrent neural network |
 | Stateful Predict | Predict responses using a trained recurrent neural network |
 | Deep Learning Object Detector | Detect objects using trained deep learning object detector |
 | TensorFlow Model Predict | Predict responses using pretrained Python TensorFlow model (Since R2024a) |
 | PyTorch Model Predict | Predict responses using pretrained Python PyTorch model (Since R2024a) |
 | ONNX Model Predict | Predict responses using pretrained Python ONNX model (Since R2024a) |
 | Custom Python Model Predict | Predict responses using pretrained custom Python model (Since R2024a) |
 | Clipped ReLU Layer | Clipped Rectified Linear Unit (ReLU) layer (Since R2024b) |
 | GELU Layer | Gaussian error linear unit (GELU) layer (Since R2024b) |
 | Leaky ReLU Layer | Leaky rectified linear unit (ReLU) layer (Since R2024b) |
 | PReLU Layer | Parameterized rectified linear unit (PReLU) layer (Since R2026a) |
 | ReLU Layer | Rectified linear unit (ReLU) layer (Since R2024b) |
 | Sigmoid Layer | Sigmoid layer (Since R2024b) |
 | Softmax Layer | Softmax layer (Since R2024b) |
 | Swish Layer | Swish layer (Since R2026a) |
 | Tanh Layer | Hyperbolic tangent (tanh) layer (Since R2024a) |
 | Addition Layer | Addition layer (Since R2024b) |
 | Concatenation Layer | Concatenation layer (Since R2024b) |
 | Depth Concatenation Layer | Depth concatenation layer (Since R2024b) |
 | Multiplication Layer | Multiplication layer (Since R2024b) |
 | Convolution 1D Layer | 1-D convolutional layer (Since R2024b) |
 | Convolution 2D Layer | 2-D convolutional layer (Since R2024b) |
 | Convolution 3D Layer | 3-D convolutional layer (Since R2024b) |
 | Fully Connected Layer | Fully connected layer (Since R2024b) |
 | Grouped Convolution 2D Layer | Grouped 2-D convolutional layer (Since R2026b) |
 | Rescale-Symmetric 1D | 1-D input layer with rescale-symmetric normalization (Since R2024b) |
 | Rescale-Symmetric 2D | 2-D input layer with rescale-symmetric normalization (Since R2024b) |
 | Rescale-Symmetric 3D | 3-D input layer with rescale-symmetric normalization (Since R2024b) |
 | Rescale-Zero-One 1D | 1-D input layer with rescale-zero-one normalization (Since R2024b) |
 | Rescale-Zero-One 2D | 2-D input layer with rescale-zero-one normalization (Since R2024b) |
 | Rescale-Zero-One 3D | 3-D input layer with rescale-zero-one normalization (Since R2024b) |
 | Zerocenter 1D | 1-D input layer with zerocenter normalization (Since R2024b) |
 | Zerocenter 2D | 2-D input layer with zerocenter normalization (Since R2024b) |
 | Zerocenter 3D | 3-D input layer with zerocenter normalization (Since R2024b) |
 | Zscore 1D | 1-D input layer with zscore normalization (Since R2024b) |
 | Zscore 2D | 2-D input layer with zscore normalization (Since R2024b) |
 | Zscore 3D | 3-D input layer with zscore normalization (Since R2024b) |
 | Batch Normalization Layer | Batch normalization layer (Since R2024b) |
 | Instance Normalization Layer | Instance normalization layer (Since R2026a) |
 | Layer Normalization Layer | Layer normalization layer (Since R2024b) |
 | Inverse Zerocenter | Inverse zero-center normalization (Since R2026a) |
 | Inverse Zscore | Inverse Z-score normalization (Since R2026a) |
 | Inverse Rescale-Zero-One | Inverse rescale-zero-one normalization (Since R2026b) |
 | Inverse Rescale-Symmetric | Inverse rescale-symmetric normalization (Since R2026b) |
 | Average Pooling 1D Layer | 1-D average pooling layer (Since R2024b) |
 | Average Pooling 2D Layer | 2-D average pooling layer (Since R2024b) |
 | Average Pooling 3D Layer | 3-D average pooling layer (Since R2024b) |
 | Global Average Pooling 1D Layer | 1-D global average pooling layer (Since R2024b) |
 | Global Average Pooling 2D Layer | 2-D global average pooling layer (Since R2024b) |
 | Global Average Pooling 3D Layer | 3-D global average pooling layer (Since R2024b) |
 | Global Max Pooling 1D Layer | 1-D global max pooling layer (Since R2024b) |
 | Global Max Pooling 2D Layer | 2-D global max pooling layer (Since R2024b) |
 | Global Max Pooling 3D Layer | 3-D global max pooling layer (Since R2024b) |
 | Max Pooling 1D Layer | 1-D max pooling layer (Since R2024b) |
 | Max Pooling 2D Layer | 2-D max pooling layer (Since R2024b) |
 | Max Pooling 3D Layer | 3-D max pooling layer (Since R2024b) |
 | Flatten Layer | Flatten layer (Since R2024b) |
 | GRU Layer | Gated recurrent unit (GRU) layer for recurrent neural network (RNN) (Since R2025a) |
 | GRU Projected Layer | Gated recurrent unit (GRU) projected layer for recurrent neural network (RNN) (Since R2025a) |
 | LSTM Layer | Long short-term memory (LSTM) layer for recurrent neural network (RNN) (Since R2024b) |
 | LSTM Projected Layer | Long short-term memory (LSTM) projected layer for recurrent neural network (RNN) (Since R2024b) |
 | Dropout Layer | Dropout layer (Since R2024b) |
 | Identity Layer | Identity layer (Since R2026a) |
 | Permute Layer | Permute layer (Since R2026b) |
 | Reshape Layer | Reshape layer (Since R2026b) |
 | Scaling Layer | Scaling layer (Since R2026a) |
 | Spatial Dropout Layer | Spatial dropout layer (Since R2026a) |
Topics
Deep Learning Layer Blocks
- List of Deep Learning Layer Blocks and Subsystems
Discover all the deep learning layer blocks and subsystems in Simulink. - Implement Unsupported Deep Learning Layer Blocks
Learn how to implement unsupported deep learning layer blocks.
Images
- Classify Image in Simulink Using SqueezeNet
This example shows how to classify an image in Simulink® using the Classify block. - Acceleration for Simulink Deep Learning Models
Improve simulation speed with accelerator and rapid accelerator modes. - Lane and Vehicle Detection in Simulink Using Deep Learning
This example shows how to use deep convolutional neural networks inside a Simulink® model to perform lane and vehicle detection. - Classify ECG Signals in Simulink Using Deep Learning
This example shows how to use wavelet transforms and a deep learning network within a Simulink (R) model to classify ECG signals. - Classify Images in Simulink with Imported TensorFlow Network
Import a pretrained TensorFlow™ network usingimportTensorFlowNetwork, and then use the Predict block for image classification in Simulink.
Sequences
- Predict and Update Network State in Simulink
This example shows how to predict responses for a trained recurrent neural network in Simulink® by using theStateful Predictblock. - Classify and Update Network State in Simulink
This example shows how to classify data for a trained recurrent neural network in Simulink® by using theStateful Classifyblock. - Speech Command Recognition in Simulink
Detect the presence of speech commands in audio using a Simulink model. - Time Series Prediction in Simulink Using Deep Learning Network
This example shows how to use an LSTM deep learning network inside a Simulink® model to predict the remaining useful life (RUL) of an engine. - Simulate Calorie Burn Using Neural Network in Simulink
This example shows how to include a simple fully connected neural network in a Simulink® model that predicts calorie burn when given five time steps of sensor readings from a smart watch. (Since R2024b) - Battery State of Charge Estimation Using Deep Learning
Define requirements, prepare data, train deep learning networks, verify robustness, integrate networks into Simulink, and deploy models. (Since R2024b) - Physical System Modeling Using LSTM Network in Simulink
This example shows how to create a reduced order model (ROM) that acts as a virtual sensor in a Simulink® model using a long short-term memory (LSTM) neural network. - Classify Motor Faults Using Deep Learning
This example shows how to train a deep learning model to classify faults in a permanent magnet synchronous motor (PMSM) using simulated data across various revolutions per minute (RPM). (Since R2025a) - Improve Performance of Deep Learning Simulations in Simulink
This example shows how to use code generation to improve the performance of deep learning simulations in Simulink®.
Reinforcement Learning
- Control Water Level in a Tank Using a DDPG Agent (Reinforcement Learning Toolbox)
Use DDPG agent to control water level in a tank modeled in Simulink. - Train DDPG Agent for Adaptive Cruise Control (Reinforcement Learning Toolbox)
Train a DDPG agent for an adaptive cruise control application. - Train DQN Agent for Lane Keeping Assist Using Parallel Computing (Reinforcement Learning Toolbox)
Train a DQN agent for an automated driving application using parallel computing. - Train DDPG Agent for Path-Following Control (Reinforcement Learning Toolbox)
Train a DDPG agent for lane following control.
Python Coexecution
- Classify Images Using TensorFlow Model Predict Block
Classify images using TensorFlow Model Predict block. - Classify Images Using ONNX Model Predict Block
Classify images using ONNX Model Predict block. - Classify Images Using PyTorch Model Predict Block
Classify images using PyTorch Model Predict block. - Predict Responses Using TensorFlow Model Predict Block
Predict Responses Using TensorFlow Model Predict block. - Predict Responses Using ONNX Model Predict Block
Predict Responses Using ONNX Model Predict block. - Predict Responses Using PyTorch Model Predict Block
Predict Responses Using PyTorch Model Predict block. - Predict Responses Using Custom Python Model in Simulink (Statistics and Machine Learning Toolbox)
This example shows how to use the Custom Python Model Predict (Statistics and Machine Learning Toolbox) block for prediction in Simulink®.
Code Generation
- Deep Learning Code Generation from Simulink Applications
Generate C/C++ and GPU code for deployment on desktop or embedded targets - Export Network to FMU
This example shows how to export a trained network as a Functional Mock-up Unit (FMU). (Since R2023b)
Featured Examples
Lane and Vehicle Detection in Simulink Using Deep Learning
Use deep convolutional neural networks inside a Simulink® model to perform lane and vehicle detection. This example takes the frames from a traffic video as an input, outputs two lane boundaries that correspond to the left and right lanes of the ego vehicle, and detects vehicles in the frame.
Classify ECG Signals in Simulink Using Deep Learning
Use wavelet transforms and a deep learning network within a Simulink (R) model to classify ECG signals. This example uses the pretrained convolutional neural network from the Classify Time Series Using Wavelet Analysis and Deep Learning example of the Wavelet Toolbox™ to classify ECG signals based on images from the CWT of the time series data. For information on training, see Classify Time Series Using Wavelet Analysis and Deep Learning (Wavelet Toolbox).
Time Series Prediction in Simulink Using Deep Learning Network
Use an LSTM deep learning network inside a Simulink® model to predict the remaining useful life (RUL) of an engine. You include the network inside the Simulink model by using a Stateful Predict block, which predicts the RUL at every simulation step.
Battery State of Charge Estimation in Simulink Using Feedforward Neural Network
Use a feedforward deep learning network inside a Simulink® model to predict the state of charge (SOC) of a battery. You include the network inside the Simulink model by using a Predict block, which predicts the SOC at every simulation step.
Profile Deep Learning Network for Deployment
Profile a deep learning network in Simulink. Profiling your network before training is a good way of checking that the network meets your requirements, before spending time on training. This example shows how to check:
Generate AUTOSAR C Code for Deep Learning Model
Integrate a trained deep neural network in a Simulink model mapped to an AUTOSAR Classic software component.
