Edge Impulse, Nordic Semi Partner to Bring High-Efficiency TinyML to the nRF52 and nRF53 Families

TinyML specialist Edge Impulse has announced a partnership with Nordic Semiconductor to bring the former's platform to the nRF52 and nRF53 systems-on-chips (SoCs) — promising rapid creation and deployment of complex machine learning tasks directly on-device.

"Together, Edge Impulse and Nordic are paving the way for every developer to eliminate time-consuming and difficult machine learning software development, deployment, and operations for Nordic silicon, in a singular powerful platform," states Edge Impulse co-founder and chief executive Zach Shelby of the partnership. "With Edge Impulse and Nordic’s nRF52840 and nRF5340 developer kits, developers can rapidly create complex motion detection, sound recognition, and image classification on low-power, memory-constrained, and remote edge devices for free, utilizing Nordic’s ubiquitous Bluetooth LE solutions."

"With this solution developers using Nordic hardware will be able to implement machine learning applications never possible before, utilizing the Edge Impulse’s Edge Optimized Neural (EON) technology to optimize memory use and inference time. Integrating ML with advanced, multi-protocol solutions from Nordic Semiconductor unlocks endless Bluetooth LE development opportunities for industrial, asset tracking, and wearable customers everywhere."

"What AI and machine learning on resource-constrained chips does — which Nordic will now collectively refer to as TinyML — is take the application potential of wireless IoT technologies such as Bluetooth to a whole new level in terms of environmental awareness and autonomous decision making," explains Nordic's director of product management Kjetil Holstad. "What our partnership with Edge Impulse will do is remove all the complexity and previous technological barriers-to-entry for our customers wishing to add TinyML features to their Bluetooth applications.:

"In fact using Edge Impulse tools, Nordic customers could be up and running TinyML on their applications within an afternoon. And at an ultra-low power consumption level that still supports extended battery operation, even from small batteries."

Edge Impulse has already published a pair of guides to getting started with the nRF52840 and nRF5340 DK development boards, and is to host a hands-on technical webinar on the topic on February 25th; those interested can register on the event page.