Auto ML Algorithms on Arm Cortex-M0 to -M4

By Chad Cox

Production Editor

Embedded Computing Design

May 08, 2023


Auto ML Algorithms on Arm Cortex-M0 to -M4
Image Credit: Qeexo

Qeexo, a TDK group company, released an automated ML platform for Arm Keil MDK delivering an extensive range of ML algorithms developed for the Cortex-M0 to -M4 class processors. It is designed to promptly analyze sensor data for ML solutions.

Reinhard Keil, senior director, embedded technology, Arm said, “By abstracting the entire ML development process with a powerful and easy-to-use graphical user interface, Qeexo AutoML enables rapid build, test, and deployment of ML models to Arm Keil MDK allowing embedded and IoT developers to harness the power of ML as they build new solutions on Arm.”

The ML model is integrated into the Arm Keil IDE employing the CMSIS-Pack mechanism for binary applications on an Arm Cortex based MCU for simplistic end-to-end ML development workflows, allowing incorporation of output libraires from Qeexo AutoML.

Qeexo AutoML creates a no-code environment allowing data analyzation and training of various ML algorithms to the same dataset. Analysis is created for accuracy, memory size, and latency for better flexibility when choosing a model.

Ideal for applications include:

  • Industrial
  • IoT
  • Wearables
  • Automotive
  • Mobile
  • Harsh environments

Sang Lee, CEO, Qeexo noted, “Qeexo AutoML’s integration with Arm Keil MDK closes the gap between machine learning and embedded development, enabling effortless integration of Qeexo AutoML models to any Arm Keil MDK project.”

Chad Cox. Production Editor, Embedded Computing Design, has responsibilities that include handling the news cycle, newsletters, social media, and advertising. Chad graduated from the University of Cincinnati with a B.A. in Cultural and Analytical Literature.

More from Chad