Ceva and Edge Impulse Join Forces to Enable Faster Development of Edge AI Applications

Ceva and Edge Impulse announced a collaboration to rapidly develop, train and deploy advanced embedded machine learning (ML) applications on Ceva's neural processing units with cycle-accurate performance, even before physical hardware is available. This first-of-its-kind collaboration based around Ceva's NPU IP ensures that developers can accurately benchmark and refine the performance of their edge AI models using Edge Impulse's platform, significantly accelerating the time-to-market.
 
As developers are intensifying their efforts to enable edge AI applications, Edge Impulse's platform for building machine learning models is a perfect extension for the Ceva-NeuPro-Nano NPU family. The Ceva-NeuPro-Nano NPU IP for Embedded AI is a highly efficient, self-sufficient NPU family designed for embedded ML applications. It delivers the optimal balance of ultra-low power and the best performance in a small area to efficiently execute embedded ML workloads on-device.

This combination is ideal for developments targeting Hearables, Wearables, Home Audio, Smart Home, Smart Factory, and more. These NPUs are ideal for Ceva's large installed base of wireless connectivity customers and MCU vendors wishing to integrate their own AI/ML models into their product roadmaps to enhance performance, and enter new market segments. 

Edge Impulse streamlines the creation of AI and machine learning models for edge hardware, allowing devices to make decisions and offer insight where data is gathered. Edge Impulse's technology allows teams to rapidly develop production-ready solutions in weeks instead of years, using powerful automations. The company's platform perfectly complements the NeuPro-Nano hardware, providing tools to deploy and benchmark embedded ML applications.

"Ceva-NeuPro-Nano is an exciting new NPU IP core that will enable a wide range of embedded ML applications to efficiently run in small, low-power and high-performance edge devices," says Zach Shelby, Co-founder and CEO, Edge Impulse. "Our first-of-its kind NPU IP collaboration unlocks the full potential of embedded ML, pre-silicon."

"We are in the early stages of the Edge AI era, with demand for on-device AI growing across every industry and market segment," adds Chad Lucien, vice president and general manager of the Sensors and Audio Business Unit at Ceva. “To address the acute demand for low-power, small form factor and powerful AI devices, Edge Impulse and NeuPro-Nano is a winning combination". Ceva's NeuPro-Nano self-sufficient architecture uniquely supports AI inference, feature extraction and the DSP workloads commonly used in audio, voice and vision applications. With Edge Impulse's tools developers are able to optimize AI performance with little to no code. Models can be uploaded to or developed using the Edge Impulse Platform for faster development cycles and deployment on NeuPro-Nano NPUs, ensuring accurate cycle count emulation for the full end-to-end AI application.

Ceva's NeuPro-Nano NPU IP is available for licensing in two configurations to address a wide variety of use cases and Edge Impulse Platform will be available for use with Ceva-NeuPro-Nano in the coming months.
www.edgeimpulse.com
www.ceva-ip.com