NanoEdge AI Studio – STMicroelectronics

AutoML tool for smarter products

With NanoEdge AI Studio, find and configure the best AI library for your embedded project.
Start integrating machine learning models with on-device learning capabilities into your STM32 microcontroller or your smart sensor with minimal investment.

Download NanoEdge AI Studio

New in version 3.3

Free and unlimited use on ST boards
(100+ ST boards supported)
Data logger tool for ST boards
Continuous improvement of ML algorithms

As easy as 1-2-3

NanoEdge AI Studio guides you through simple steps to create anomaly detection, classification or regression libraries. Follow the instructions step by step to collect, validate your data, and generate the C-code to be integrated in your project.

Project settings

Signals

Benchmark

Emulator

Validation

Deployment

Select your hardware, the type of signal, and the memory you want to allocate to your project. Optimize the settings to generate your machine learning libraries.

Upload from files, use the embedded datalogger or stream the signal you need for your project through USB.

Launch the automatic benchmark to find the right combinations of signal preprocessing, Machine Leaning algorithms and hyper-parameterization for your project. Then choose the library among a pre-selection based on the most suitable level of accuracy, confidence, and memory footprints.

Evaluate the libraries you generated directly on the studio with data streamed in real time.

Generate detailed reports of your AI libraries to compare them with further tests, and select the one you wish to embed in your final product.

Generate optimized C-code for STM32 MCUs and embed the AI library directly in your project in a few clicks. You’re ready to go!

From idea to datalogging, in a matter of minutes

Capturing data is essential to start your project. This step can be complex and time consuming, which is why the Studio features an embedded datalogging function.
The Studio’s datalogging feature helps you acquire and manage high-speed data on the STWIN development board. You can work with your industrial-grade sensors without having to write a single line of code! Simply connect your board to your serial port, launch NanoEdge AI Studio and get started.