Microchip Technology has partnered with Cartesiam, Edge Impulse and Motion Gestures to simplify ML implementation at the edge utilising the company’s ARM Cortex based 32-bit micro-controllers and microprocessors in its MPLAB X IDE. Bringing the interface to these partners’ software and solutions into its design environment uniquely places the company to be able to support customers through all stages of their AI/ML projects including data gathering, training the models and inference implementation.
“Adoption of our 32-bit MCUs in AI-at-the-edge applications is growing rapidly, and now these designs are easy for any embedded system developer to implement,” said Fanie Duvenhage, vice president of Microchip’s human-machine interface and touch function group. “It is also easy to test these solutions using our ML evaluation kits such as the EV18H79A or EV45Y33A.”
Unlike conventional solutions, the company’s platform does not need any training data collection or programming and employs advanced machine learning algorithms. Subsequently, gesture software development time and costs are decreased by 10x while gesture recognition accuracy is improved to nearly 100%.