Nuvoton Introduces Endpoint AI Platform, Ready for Machine Learning Applications

Nuvoton, a leading microcontroller platform provider, has launched its new Endpoint AI Platform that aims to accelerate the development of fully-featured microcontroller AI products. This platform is powered by Nuvoton’s advanced MCU and MPU silicon, including the NuMicro M55M1 with Ethos U55 NPU, NuMicro MA35D1, and NuMicro M467 series.

The NuMicro M55M1 series microcontroller is specifically designed for machine learning applications, with the Ethos-U55 NPU and on-device AI features that are suitable for embedded applications. This MCU allows the system to monitor events using image sensors, microphones, and sensors while in low-power mode, without waking up the central processor. It also includes an ML model protection mechanism to enhance security against potential hacking attempts.

One of the notable features of these processors is their support for ARM Helium technology, which provides a significant performance boost for machine learning and digital signal processing applications in small, low-power embedded systems.

The NuMicro MA35D1 series is a heterogeneous multi-core microprocessor that serves as a high-end Edge IIoT Gateway. It is equipped with a dual-core 64-bit Arm Cortex-A35 core and a 180 MHz Arm Cortex-M4, enabling Tiny AI/ML edge computing.

For a wide range of applications such as Smart Home appliances, IoT gateways, industrial control, telecommunications, and data centers, the M467 series is an ideal choice. It is a 32-bit microcontroller based on the Arm Cortex-M4F core with a built-in DSP instruction set and single precision floating-point unit (FPU). The M467 offers a rich set of connectivity, I/O, and security peripherals, making it highly versatile for IoT tasks.

To support these hardware platforms, Nuvoton provides fully-featured development boards and a comprehensive set of development tools. The NuMaker MA35D1 development board, for instance, enables efficient machine learning projects, including image classification, and presents analysis to the user intuitively via the Human Machine Interface (HMI). The NuMaker-IoT-M467 development board is specifically designed for IoT applications of the M467 MCU.

To simplify the development of TinyML applications, Nuvoton offers the NuEdgeWise IDE (Integrated Development Environment). This machine-learning tool supports the key stages of ML application development, including labeling, training, validation, and testing. Leveraging the popular Jupyter Notebook platform, developers can train and deploy models on Nuvoton chips using TensorFlow Lite, making TinyML applications more accessible and easier to implement.

With its powerful hardware platforms and user-friendly development tools, Nuvoton demonstrates its commitment to providing a complete Endpoint AI Ecosystem. These solutions are well-suited for various applications such as smart home appliances, security systems, smart city services, industry, agriculture, entertainment, environmental protection, education, voice-control tasks, and sports, health, and fitness.

Background Information

---

About ARM: ARM, originally known as Acorn RISC Machine, is a British semiconductor and software design company that specializes in creating energy-efficient microprocessors, system-on-chip (SoC) designs, and related technologies. Founded in 1990, ARM has become a important player in the global semiconductor industry and is widely recognized for its contributions to mobile computing, embedded systems, and Internet of Things (IoT) devices. ARM's microprocessor designs are based on the Reduced Instruction Set Computing (RISC) architecture, which prioritizes simplicity and efficiency in instruction execution. This approach has enabled ARM to produce highly efficient and power-saving processors that are used in a vast array of devices, ranging from smartphones and tablets to IoT devices, smart TVs, and more. The company does not manufacture its own chips but licenses its processor designs and intellectual property to a wide range of manufacturers, including Qualcomm, Apple, Samsung, and NVIDIA, who then integrate ARM's technology into their own SoCs. This licensing model has contributed to ARM's widespread adoption and influence across various industries.