ADI and Antmicro’s AutoML for Embedded Builds AI Models for Edge Hardware

AutoML for Embedded, developed by Analog Devices (ADI) and Antmicro, is available now to help developers easily build, optimize, and deploy AI models on constrained edge hardware. The tool is built into Visual Studio Code as a plugin. It’s part of the Kenning framework. Whether you're working with ADI’s MAX78002 or MAX32690 AI MCUs, or simulating your project using Renode and the Zephyr RTOS, the setup allows you to deploy AI models, all without deep machine learning expertise. 

In essence, AutoML for Embedded uses advanced algorithms like SMAC and Hyperband to automate model search and tuning. Further, it checks memory limits, benchmarks performance, and helps ensure your model is lightweight enough to run smoothly on your device. The tool is already in action, being used to deploy robust models in real-world scenarios from image classification on low-power cameras to anomaly detection in industrial sensors. 

An anomaly-detection model generated with AutoML for Embedded was deployed on an actual microcontroller (ADI MAX32690) as well as on its virtual self, simulated using Renode. AutoML for Embedded is open-source and currently available on the Visual Studio Code Marketplace and GitHub.