Follow Datanami:
September 23, 2020

Qeexo Adds Support for Arm’s Edge Processor

Qeexo, the “tinyML” specialist, said its AutoML platform now supports the smallest Cortex processors from Arm Ltd., making it the first vendor to automate machine learning on the Arm processor used for edge computing in sensors and microcontrollers.

The Carnegie Mellon University spinoff said Wednesday (Sept. 23) its AutoML platform that migrated to the cloud this past summer supports Arm’s Cortex-MO and -MO+ architectures aimed at edge computing applications. The “plus” version further reduces power consumption, a critical requirement for Internet of Things sensors and other unattended devices.

The Cortex-MO product line targets embedded applications and smart, connected devices used in industrial, automotive and other edge deployments.

“The added support of the Qeexo AutoML platform enables application developers to easily add intelligence to small devices such as wearables, making a world of one trillion intelligent devices a closer reality,” said Steve Roddy, vice president of product marketing for Arm’s Machine Learning Group.

Qeexo said its support for the Arm devices would enable edge processing for ever-smaller devices. The spinoff’s machine learning models are designed to run locally on embedded devices that require ultra-low power consumption for low-latency applications running on microcontrollers.

The company also cited a growing list of machine learning algorithms supported by its AutoML platform, including Decision Tree, GBM, Logistic Regression, Random Forest and XGBoost.

Support for the Arm processors and tinyML’s migration to the cloud illustrate how the startup and others are pushing machine intelligence out to edge devices.

“What we really want to tell the market is that even those microcontrollers that are already out and that have very limited memory resource and processing power, you can still have a commercially viable ML solution running on it, if you use the right tool,” Sang Won Lee, Qeexo’s co-founder and CEO, told Datanami earlier this year.

“You don’t want to neglect all the sensor data that’s connected to the microcontroller,” Lee added. “We can provide a tool that you can use to build intelligence that can be embedded into those tools.”

Qeexo other partners include embedded chip vendors Renesas and STMicroelectronics along with Bosch Sensortec and the open source prototyping platform Arduino. For example, Qeexo works with STMicroelectronics on industry IoT applications such as predictive maintenance.

Lee added that the combination of Arm-based microcontrollers and its automated machine learning platform also would help accelerate development of smart edge applications.

Recent items:

Machine Learning at the Edge, Hold the Code

On the Radar: Cortex Labs, RadicalBit, Qeexo