MATLAB and Simulink for Edge AI

Deploy machine learning and deep learning applications to embedded systems

Simulate, test, and deploy machine learning and deep learning models to edge devices and embedded systems. Generate code for complete AI applications, including pre-processing and post-processing algorithms.

With MATLAB^® and Simulink^®, you can:

Generate optimized C/C++ and CUDA code for deployment to CPUs and GPUs
Generate synthesizable Verilog and VHDL code for deployment to FPGAs and SoCs
Accelerate inference with hardware-optimized deep learning libraries, including oneDNN, Arm Compute Library, and TensorRT
Incorporate pre-trained TensorFlow Lite (TFLite) models into applications deployed to hardware
Compress AI models for inference on resource-constrained hardware with tools for hyperparameter tuning, quantization, and network pruning

“From data annotation to choosing, training, testing, and fine-tuning our deep learning model, MATLAB had all the tools we needed—and GPU Coder enabled us to rapidly deploy to our NVIDIA GPUs even though we had limited GPU experience.”
Valerio Imbriolo, Drass Group

Screenshot of C/C++ code being deployed to an image of embedded hardware.

CPUs and Microcontrollers

Generate portable, optimized C/C++ code from trained machine learning and deep learning models with MATLAB Coder™ and Simulink Coder™. Optionally include calls to vendor-specific libraries for deep learning inference in the generated code, such as oneDNN and Arm^® Compute Library.

Code Generation for Image Classification with Machine Learning

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

Compress Image Classification Network for Deployment to Resource-Constrained Embedded Devices

Generate Code for TensorFlow Lite (TFLite) Model and Deploy on Raspberry Pi

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

GPUs

Generate optimized CUDA^® code for trained deep learning networks with GPU Coder™. Include pre-processing and post-processing along with your networks to deploy complete algorithms to desktops, servers, and embedded GPUs. Use NVIDIA^® CUDA libraries, such as TensorRT™ and cuDNN, to maximize performance.

Code Generation for Object Detection Using YOLO v4 Deep Learning

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.

FPGAs and SoCs

Prototype and implement deep learning networks on FPGAs and SoCs with Deep Learning HDL Toolbox™. Program deep learning processors and data movement IP cores with pre-built bitstreams for popular FPGA development kits. Generate custom deep learning processor IP cores and bitstreams with HDL Coder™.

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

Use MATLAB to Prototype Deep Learning on an Intel FPGA (3:24)

Deploy Neural Network Regression Model to FPGA/ASIC Platform

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

AI Model Compression

Reduce memory requirements for machine learning and deep learning models with size-aware hyperparameter tuning and quantization of weights, biases, and activations. Minimize the size of a deep neural network by pruning insignificant layer connections.

Compress Machine Learning Model for Memory-Limited Hardware

Fixed-Point Code Generation for Prediction of SVM

Deep Network Quantizer (Examples)

Parameter Pruning and Quantization of Image Classification Network

Compressing Neural Networks Using Network Projection