Ultra-low-power edge AI specialist Syntiant has teamed up with Edge Impulse to launch a device it hopes will bring its technology to a far broader audience: The TinyML Development Board, aimed at "both technical and non-technical users" and powered by the company's NDP101 Neural Decision Processor.
"Syntiant’s TinyML board is another example of how we are advancing AI pervasiveness by moving machine learning from the cloud to the edge," claimed Kurt Busch, Syntiant chief executive, of the launch. "Our collaboration with Edge Impulse now enables anyone, from individual developers and hardware engineers to small companies to design, build and deploy highly accurate ML applications that respond to speech, sounds and motion with minimal power consumption. Whether it is for a wearable, industrial product or even to assist with people with disabilities, the possibilities are endless with our new TinyML board that provides a full solution for bringing the power of artificial intelligence to almost any device."
Build around the NDP101 Neural Decision Processor, rather than the more recently-announced NDP200, the compact development board includes a Microchip SAMD21 central processor with a 48MHz Arm Cortex-M0+ core, 32kB of static RAM (SRAM), and 256kB of flash memory, 2MB of serial flash, a user-accessible RGB LED, a microSD Card slot, a BMI160 six-axis motion sensor, and an SPH0651LM4H microphone, plus five digital input/output pins designed to be compatible with code written for Arduino MKR Zero devices and offering one UART and one I2C bus.
The hardware is supported by Edge Impulse's Studio platform, allowing even non-coders to get started quickly. "In Edge Impulse's pursuit to democratize embedded machine learning for all developers, we are thrilled to partner with Syntiant, which has become a trailblazer in the ultra-low-power edge AI space," Zach Shelby, co-founder and chief executive of Edge Impulse, said of the partnership.
"Our front-end support for the Syntiant TinyML Development Board provides customers with all the software tools necessary for building and deploying limitless ML applications that will unlock the next generation of always-on devices."
According to Syntiant's testing, the board allows deep learning applications for speech run at under 140 microwatts and sensor applications to run at under 100 microwatts, a claimed 20x boost in throughput and 200x improvement in efficiency compared to traditional edge AI microcontroller boards. An on-board micro-USB port provides power and data connectivity, while the board can also be powered by an optional 3.7V lithium-polymer battery for mobile projects.