Machine Learning Suite Marries ML with MCU and MPU

By Ken Briodagh

Senior Technology Editor

Embedded Computing Design

September 14, 2023

Story

Machine Learning Suite Marries ML with MCU and MPU

The path to industrial automation runs right through the machine learning curve, and every major player is looking to make those computing loads easier to bear.

According to a recent release from Microchip Technology, the company has launched a new integrated workflow to help engineers and developers bring ML into their embedded systems easier than ever.

The MPLAB Machine Learning Development Suite is a software toolkit that is designed to make it easy for system designers to add ML inference to microcontrollers (MCUs) and microprocessors (MPUs) within the Microchip ecosystem of products. The company says it’s the first to integrate with not just 32-bit MCU and MPU, but also 8- and 16-bit devices.

“Machine Learning is the new normal for embedded controllers and utilizing it at the edge allows a product to be efficient, more secure and use less power than systems that rely on cloud communication for processing,” said Rodger Richey, VP, Development Systems business unit, Microchip.

The company says that a key use case for its customers will be to allow them to create predictive maintenance solutions that will accurately forecast potential issues with equipment, reducing downtime and repair rollouts in industrial, manufacturing, consumer, and automotive applications.

The MPLAB Machine Learning Development Suite is powered by AutoML, according to the release, and Microchip says that the new toolkit can eliminate repetitive, tedious and time-consuming model-building tasks including extraction, training, validation and testing. It can also provide model optimizations so it doesn’t exceed the memory constraints of MCU and MPUs.

Microchip also said it offers the option to bring a model from TensorFlow Lite and use it in any MPLAB Harmony v3 project. In addition, the VectorBlox Accelerator Software Development Kit (SDK) offers a Convolutional Neural Network (CNN)-based Artificial Intelligence/Machine Learning (AI/ML) inference with PolarFire FPGA.

Pricing varies based on licensing. A free version of the MPLAB Machine Learning Development Suite is available for evaluation. For additional information or to purchase, click here to visit Microchip.

Ken Briodagh is a writer and editor with two decades of experience under his belt. He is in love with technology and if he had his druthers, he would beta test everything from shoe phones to flying cars. In previous lives, he’s been a short order cook, telemarketer, medical supply technician, mover of the bodies at a funeral home, pirate, poet, partial alliterist, parent, partner and pretender to various thrones. Most of his exploits are either exaggerated or blatantly false.

More from Ken