MATLAB and Simulink for Embedded AI

Deploy machine learning and deep learning applications to embedded systems

With MATLAB and Simulink, you can design, simulate, test, verify, and deploy AI algorithms that enhance the performance and functionality of complex embedded systems.

Illustration of the Embedded AI workflow.

Why MATLAB and Simulink?

Resource-Constrained Deployment

Automatically generate code optimized for deployment for entire embedded AI applications.

Code Generation for Deep Learning Models

Code Generation for Machine Learning Models

Simulation and Testing with Simulink

Use AI with Simulink to simulate and test the integration of AI models into complex systems.

Deep Learning with Simulink

Battery State of Charge Estimation Using Deep Learning

Access to Pretrained AI Models

Leverage built-in pretrained models and models from PyTorch^® and TensorFlow™.

Pretrained Deep Learning Models

Convert Deep Learning Models Between PyTorch and MATLAB

Verification for Safety-Critical Systems

Develop complex AI-powered embedded systems for safety-critical and industrial applications.

AI Verification Library

Verification and Validation for AI with MATLAB and Simulink

Using MATLAB and Simulink for Deployment to Embedded AI

Discover how you can prepare AI models and automatically generate code to deploy embedded AI applications to CPUs, GPUs, FPGAs, NPUs, and more. Explore tutorials, examples, and videos for practical advice on embedded AI with MATLAB and Simulink.

Screenshot of a layered graph, calibration statistics, and validation results to optimize AI models for embedded deployment.

Deploy to CPUs and Microcontrollers

Generate portable, optimized C/C++ code from trained machine learning and deep learning models with MATLAB Coder and Simulink Coder.

Developing and Embedding AI-Based SOC Estimation for BMS Using MATLAB (7:52)

How to Develop and Deploy a Neural Network for MCUs in 4 Steps (3:41)

Generate Generic C/C++ Code for Deep Learning Networks

Code Generation for LSTM Network on Raspberry Pi

Screenshot of C/C++ code in Simulink being deployed to images of a NVIDIA desktop and embedded GPU.

Deploy to GPUs

Generate optimized CUDA^® code for trained deep learning networks with GPU Coder for deployment to desktops, servers, and embedded GPUs.

Code Generation for Detecting Defects on Printed Circuit Boards Using YOLOX Network

Deep Learning Prediction by Using NVIDIA TensorRT

Code Generation for a Deep Learning Simulink Model to Classify ECG Signals

Running FPGA-based deep learning inference on prototype hardware from MATLAB, then generating a deep learning HDL IP core for deployment on any FPGA or ASIC.

Deploy to FPGAs and SoCs

Prototype and implement deep learning networks on FPGAs and SoCs with Deep Learning HDL Toolbox. Generate custom deep learning processor IP cores and bitstreams with HDL Coder.

Use MATLAB to Prototype Deep Learning on a Xilinx FPGA (3:25)