Simplifying AI-at-the-edge design using 32-bit MCUs: Microchip partners with machine learning software leaders

15 September 2020

Microchip_Simplifying AI-at-the-edge design using 32-bit MCUs_580x280

Cartesiam, Edge Impulse & Motion Gestures integrate their machine learning (ML) offerings into Microchip’s MPLAB® X Development Environment for use with its 32-bit microcontrollers & microprocessors.

Microchip Technology has announced it has partnered with Cartesiam, Edge Impulse and Motion Gestures to simplify AI (artificial intelligence) and machine learning (ML) implementation at the edge using the company’s ARM Cortex-based 32-bit microcontrollers (MCUs) and microprocessors (MPUs) in its MPLAB X Integrated Development Environment (IDE). Bringing the interface to these partners’ software and solutions into its design environment uniquely positions Microchip to support customers through all phases 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 (HMI) & Touch Function group. “It is also easy to test these solutions using our ML evaluation kits, such as the EV18H79A or EV45Y33A.

About the partner offerings
Cartesiam
, founded in 2016, is a software publisher specialising in artificial intelligence development tools for microcontrollers. NanoEdge AI™ Studio, Cartesiam’s patented development environment, allows embedded developers, without any prior knowledge of AI, to rapidly develop specialised machine learning libraries for microcontrollers. Devices leveraging Cartesiam's technology are already in production at hundreds of sites throughout the World.

Edge Impulse is the end-to-end developer platform for embedded machine learning, enabling enterprises in industrial, enterprise and wearable markets. The platform is free for developers, providing dataset collection, DSP and ML algorithms, testing and highly efficient inference code generation across a wide range of sensor, audio and vision applications. Get started in just minutes thanks to integrated Microchip MPLAB X and evaluation kit support.

Motion Gestures, founded in 2017, provides powerful embedded AI-based gesture recognition software for different sensors, including touch, motion (such as IMUs) and vision. Unlike conventional solutions, the company’s platform does not require any training data collection or programming and uses advanced machine learning algorithms. As a result, gesture software development time and costs are reduced by 10x, while gesture recognition accuracy is increased to nearly 100%.

See demonstrations during Embedded Vision Summit
The MPLAB X IDE ML implementations will be featured during the Embedded Vision Summit 2020 virtual conference, September 15-17. Attendees can see video demonstrations at the company’s virtual exhibit, which will be staffed each day from 10:30am to 1pm PDT. 

Please let us know if you would like to speak to a subject matter expert on Microchip’s enhanced MPLAB X IDE for ML implementations, or the use of 32-bit microcontrollers in AI-at-the-edge applications. For more information, please visit: microchip.com/ML

Microchip’s offering of ML development kits now includes:
•    EV18H79A: SAMD21 ML Evaluation Kit with TDK 6-axis MEMS
•    EV45Y33A: SAMD21 ML Evaluation Kit with BOSCH IMU
•    SAMC21 xPlained Pro evaluation kit (ATSAMC21-XPRO) plus its QT8 xPlained Pro Extension Kit (AC164161):  available for evaluating the Motion Gestures solution.
•    VectorBlox Accelerator Software Development Kit (SDK): enables developers to create low-power, small-form-factor AI/ML applications on Microchip’s PolarFire FPGAs.


Contact Details and Archive...

Print this page | E-mail this page