AI tool automates machine learning process

Analog Devices Inc. (ADI) has recently unveiled a groundbreaking tool called AutoML for Embedded, designed to revolutionize the field of edge AI by streamlining the machine learning process from start to finish. Developed in collaboration with Antmicro, this innovative AI tool is now an integral part of the Kenning framework, seamlessly integrated into the CodeFusion Studio platform.

The Kenning framework serves as a versatile and open-source platform specifically tailored for optimizing, benchmarking, and deploying AI models on edge devices. By automating the end-to-end machine learning pipeline, AutoML for Embedded empowers developers of all backgrounds to create high-quality, efficient models without requiring extensive data science expertise.

During a recent demonstration, AutoML for Embedded was utilized to construct an anomaly detection model for sensory time series data on the ADI MAX32690 MCU. The AI model was successfully deployed on both physical hardware and its digital twin in Renode simulation, showcasing seamless integration and real-time performance monitoring capabilities.

As the demand for intelligent edge devices continues to rise and AI technology rapidly advances, developers are faced with the challenge of adapting powerful models to fit onto compact microcontrollers. The complexities of data preprocessing, model selection, hyperparameter tuning, and hardware-specific optimizations present significant hurdles for developers seeking to leverage AI at the edge.

Recognizing this need, Analog Devices Inc. collaborated on the development of AutoML for Embedded, a tool that empowers developers to effortlessly build and deploy robust machine learning models on edge devices, such as microcontrollers, without the burden of navigating intricate code or hardware constraints.

AutoML for Embedded, a Visual Studio Code plugin built on the Kenning library, offers support for ADI MAX78002 AI accelerator MCUs and MAX32690 devices, enabling developers to deploy models directly onto cutting-edge edge AI hardware. By leveraging Renode-based simulation and Zephyr RTOS workflows, developers can rapidly prototype and test their models, ensuring seamless integration and efficient performance monitoring.

The tool also provides access to a range of general-purpose, open-source tools that facilitate flexible model optimization without the risk of platform lock-in. By automating model search and optimization using advanced algorithms like SMAC and Hyperband with Successive Halving, AutoML for Embedded streamlines the process of exploring model architectures and training parameters, ultimately leading to successful model deployment.

Michael Gielda, VP of Business Development at Antmicro, emphasized the significance of this development, stating, "Building on the flexibility of our open-source AI benchmarking and deployment framework, Kenning, we were able to develop an automated flow and VS code plugin that vastly reduces the complexity of building optimized edge AI models. Enabling workflows based on proven open-source solutions is the backbone of our end-to-end development services that help customers take full control of their product."