STMicroelectronics, a leading global semiconductor company, has recently introduced a groundbreaking series of microcontrollers that integrate embedded artificial intelligence (AI) and accelerated machine learning (ML) capabilities. This launch, described as a significant step towards enhancing AI functionality at the edge, aims to equip cost-sensitive and power-sensitive consumer and industrial products with enhanced features in computer vision, audio processing, sound analysis, and various other algorithms previously unmanageable for smaller embedded systems.
The STM32N6 microcontroller (MCU) series is recognised by STMicroelectronics as their most powerful offering to date and is distinguished as the first to include the company's proprietary neural processing unit (NPU), the Neural-ART Accelerator. This technology reportedly offers a staggering 600 times more machine-learning performance compared to a high-end STM32 MCU currently on the market.
The chip series, which became available to select customers in October 2023, is now ready for commercial scale deployment. Early adopters of the STM32N6 include major firms such as LG Electronics, Lenovo Research, Alps Alpine, Carlo Gavazzi, Meta-bounds, and Autotrak, all of whom have shared their positive experiences with this new technology.
Remi El-Ouazzane, President of Microcontrollers, Digital ICs, and RF Products Group (MDRF) at STMicroelectronics, commented, "We are on the verge of a significant transformation at the tiny edge. This transformation involves the increasing augmentation or replacement of our customers' workloads by AI models. Currently, these models are used for tasks such as segmentation, classification, and recognition. In the future, they will be applied to new applications yet to be developed."
The introduction of the Neural-ART Accelerator within the STM32N6 represents a pioneering move in AI hardware for STMicroelectronics. "The STM32N6 is the first STM32 product to feature our Neural-ART Accelerator NPU. It will utilise a new release of our unique AI software ecosystem package. This marks the beginning of a long journey of AI hardware-accelerated STM32, which will enable innovations in applications and products in ways not possible with any other embedded processing solution," El-Ouazzane elaborated.
To further bolster the capabilities of the STM32N6, STMicroelectronics is collaborating with Edge Impulse, a platform dedicated to building, deploying, and scaling edge machine learning models. This partnership is aimed at enhancing the development process for edge-capable AI algorithms, ranging from data collection to model deployment. Edge Impulse will also provide numerous generative AI-based capabilities, including AI labelling and integrations with Nvidia's TAO and Omniverse, thus complementing its existing collaboration with Nvidia.
According to STMicroelectronics, developers and enterprises can take full advantage of the STM32N6 and accelerate application development across a wide spectrum, including computer vision for both industrial and consumer uses, energy management, and anomaly detection. Zach Shelby, CEO and co-founder of Edge Impulse, remarked, "The STM32N6 is the perfect complement to the Edge Impulse platform. With its powerful AI capabilities and energy-efficient design, it aligns perfectly with our mission to make edge AI accessible and impactful across every sector."
Patrick Aidoune, General Purpose MCU Division General Manager at STMicroelectronics, added, "By combining our state-of-the-art Neural-ART Accelerator with the intuitive tools from Edge Impulse, we are empowering developers to bring sophisticated AI capabilities directly to the edge."
This announcement was made during the STM32 Summit, which is currently taking place from December 10 to 13, 2024.
Source: Noah Wire Services