ML tool suite for 8, 16 and 32bit microcontrollers
Microchip has developed a machine learning development tool suite that it says is the first to support 8bit, 16bit and 32bit microcontrollers and 32bit embedded microprocessors.
The workflow for streamlined ML model development in Microchip’s MPLAB Machine Learning Development Suite can be used across the whole range of devices with RISC-V, ARM and legacy AVR cores as well as FPGAs..
ML algorithms curate patterns from large data sets to enable decision making, for example for predictive maintenance software that accurately forecasts potential issues with equipment used in a variety of industrial, manufacturing, consumer and automotive applications.
The MPLAB Machine Learning Development Suite is powered by the open source AutoML to eliminate many repetitive, tedious and time-consuming model-building tasks including extraction, training, validation and testing. It also provides model optimizations so the memory constraints of MCU and MPUs are respected.
When used with the MPLAB X Integrated Development Environment (IDE), the toolkit can be implemented by those with little to no ML programming knowledge, which can eliminate the cost of hiring data scientists. s
It is also sophisticated enough for more experienced ML designers to use with models from TensorFlow Lite in any MPLAB Harmony v3 project. This i a fully integrated embedded software development framework that provides flexible and interoperable software modules.
The VectorBlox Accelerator Software Development Kit (SDK) also offers power-efficient Convolutional Neural Network (CNN)-based Artificial Intelligence/Machine Learning (AI/ML) inference on Microchip’s PolarFire FPGAs.
“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 of Microchip’s Development Systems business unit. “Microchip’s unique, integrated solution is designed for embedded engineers and is the first to support not just 32-bit MCUs and MPUs, but also 8- and 16-bit devices to enable efficient product development.”
Pricing varies based on licensing. A free version of the MPLAB Machine Learning Development Suite is available for evaluation.
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
