Infineon partners with Edge Impulse to extend its edge AI capabilities

Infineon partners with Edge Impulse to extend its edge AI capabilities Duncan is an award-winning editor with more than 20 years experience in journalism. Having launched his tech journalism career as editor of Arabian Computer News in Dubai, he has since edited an array of tech and digital marketing publications, including Computer Business Review, TechWeekEurope, Figaro Digital, Digit and Marketing Gazette.


Infineon Technologies AG has teamed up with Edge Impulse to extend its Tiny Machine Learning-based AI development tools for the PSoC 63 Bluetooth LE microcontroller (MCU).

Developers of AI-enabled IoT applications can now also build edge Machine Learning (ML) applications using the Edge Impulse Studio environment for deployment on high-performance, low-power PSoC 63 Bluetooth LE MCUs.

This collaboration allows customers added flexibility and choice-of-platforms to natively develop and configure ML applications for systems based on PSoC 63 Bluetooth LE MCU devices, which provide 150-MHz Arm CPU performance with low-power connectivity and a rich suite of peripheral options. For example, the CY8CKIT-062-BLE Pioneer Kit coupled with the E-Ink Display Shield Board (CY8CKIT-028-EPD) incorporates an inertial measurement unit, microphone, and temperature sensor. This supports applications that collect real-world sensor data for processing by Tiny Machine Learning-based AI models in systems optimized for low-power, low-cloud-cost edge IoT environments.

Infineon’s PSoC 63 Bluetooth LE MCU devices feature a dual-core Arm Cortex-M4F and Arm Cortex-M0+ chip architecture, Bluetooth LE 5.2, configurable voltage and frequency settings, built-in hardware-based security, state-of-the-art capacitive interfaces, and more, on a single chip. As the only 150 MHz Bluetooth LE MCU on the market, this variant of the Infineon PSoC device family is a powerful combination of power efficiency, size, and programmability making it perfectly suited for edge IoT applications that benefit from the ability to run advanced ML algorithms.

Edge Impulse’s products streamline the entire process of collecting and structuring data sets, designing algorithms with pre-built building blocks, validating the models with real-time data, and deploying the fully optimized production-ready results to edge targets such as the PSoC 63 Bluetooth LE MCU.

Shantanu Bhalerao, VP of the Bluetooth Product Line at Infineon, said: “By collaborating with Edge Impulse on the PSoC 63 Bluetooth LE MCU, Infineon customers can bring their solutions faster to market for embedded AI/ML use cases. Infineon is committed to enable our customers to develop their own AI/ML models, or use a model out of suite of predefined models available from Infineon or our valuable partners. Infineon is excited to add Edge Impulse to our growing partner network, and will continue to work with our extensive group of AI/ML partners that complements our offerings.”

Zach Shelby, CEO and co-founder of Edge Impulse, said: “With its advanced processing capabilities and low power consumption, the PSoC 63 Bluetooth LE MCU is an ideal vehicle for the next generation of edge devices, from wearables to industrial monitoring.

“Matched with the Edge Impulse platform, embedded developers can more quickly develop and deploy powerful solutions for an exciting range of edge ML applications.”

Want to learn more about edge computing from industry leaders? Check out Edge Computing Expo taking place in Amsterdam, California and London. 

Explore other upcoming enterprise technology events and webinars powered by TechForge here.

Author

  • Duncan MacRae

    Duncan is an award-winning editor with more than 20 years experience in journalism. Having launched his tech journalism career as editor of Arabian Computer News in Dubai, he has since edited an array of tech and digital marketing publications, including Computer Business Review, TechWeekEurope, Figaro Digital, Digit and Marketing Gazette.

Tags: ,

View Comments
Leave a comment

Leave a Reply