Solution makes edge AI accessible, efficient and scalable for everyone

Analog Devices, Inc. has introduced AutoML for Embedded, co-developed with Antmicro, which is now available as part of the Kenning framework and incorporated into CodeFusion Studio.

As AI rapidly moves to the edge and demand for intelligent edge devices explodes, developers are predicted to move faster. Yet, they are struggling to fit powerful models onto tiny MCUs and face a steep learning curve. Recognising this need, the company co-developed AutoML for Embedded to make edge AI accessible, efficient and scalable for everyone.

AutoML for Embedded streamlines the process by automating the end-to-end machine learning pipeline, enabling developers without data science expertise to build high-quality and efficient models that deliver robust performance. In a recent demonstration, the tool was utilised to create an anomaly detection model for sensory time series data on the ADI MAX32690 MCU. The model was deployed on physical hardware and its digital twin in Renode simulation, showcasing seamless integration and real-time performance monitoring.