MPLAB suite streamlines ML model development
Microchip has introduced the MPLAB Machine Learning development suite to support engineers incorporating machine learning into microcontrollers and microprocessors.
The software toolkit can be used across Microchip’s portfolio of microcontrollers and microprocessors from eight-, 16- and 32bit devices. “Machine Learning is the new normal for embedded controllers and utilising 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, vice president of Microchip’s Development Systems business unit.
ML uses a set of algorithmic methods to curate patterns from large data sets to enable decision making. It is typically faster, more easily updated and more accurate than manual processing. It can be used to enable predictive maintenance solutions, for example, to forecast potential issues with equipment used in a variety of industrial, manufacturing, consumer and automotive applications.
The MPLAB Machine Learning development suite helps engineers build highly efficient, small-footprint machine learning models. Powered by AutoML, the toolkit eliminates many repetitive, tedious and time-consuming model-building tasks including extraction, training, validation and testing, said Microchip. It also provides model optimisations so the memory constraints of microcontroller and microprocessors are respected.
When used in combination with the MPLAB X Integrated Development Environment (IDE), the toolkit can be implemented by those with little to no machine learning programming knowledge, said Microchip. While this can reduce the cost of hiring data scientists, the tool is also sophisticated enough for more experienced machine learning designers to control, pointed out the company.
Microchip also offers the option to bring a model from TensorFlow Lite and use it in any MPLAB Harmony v3 project, a fully integrated embedded software development framework that provides interoperable software modules to simplify the development of value-added features and reduce time to market.
There is also the VectorBlox Accelerator software development kit (SDK) which offers what is claimed to be the most power-efficient convolutional neural network (CNN)-based artificial intelligence / machine learning inference with PolarFire FPGAs.
According to Microchip, the MPLAB Machine Learning development suite provides the tools necessary for designing and optimising edge products running ML inference.
A free version of the MPLAB Machine Learning Development Suite is available for evaluation. Pricing varies based on licensing.