Syntiant Brings Artificial Intelligence Development with Introduction of TinyML Platform
October 04, 2021
Syntiant Corp unveiled its TinyML Development Board, a developer kit aimed at both technical and non-technical users building machine learning-powered applications in smart products, such as speech commands, wake word detection, acoustic event detection, and other sensor use cases.
Equipped with the ultra-low-power Syntiant NDP101 Neural Decision Processor, the TinyML board can enable speech and sensor applications to run at under 140 and 100 microwatts, respectively, delivering 20x more throughput and 200x efficiency improvement compared to traditional MCU-based systems, according to the company.
Sized at 24 mm x 28 mm, the Syntiant TinyML board is a small, self-contained system that allows trained models to be downloaded via Edge Impulse through a micro-USB connection without the need for any specialized hardware. The new board also is fully compatible with Arduino's open-source platform.
Users can sample raw data, build, download, and deploy trained embedded machine learning models by using the Edge Impulse studio to create low-power, high-performance speech, audio and sensor interfaces.
The TinyML platform's onboard digital microphone and motion sensor enable configuration for any speech, event detection, or 6 axis motion- and vibration-related application. Shipping with a built-in "Alexa play music" model, key product features include:
- Syntiant NDP101 Neural Decision Processor
- Syntiant Core 1 neural network
- Supports up to 560k parameters and 64 output classifications
- Host processor: Cortex-M0+ 32bit low power ARM MCU, including:
- 256KB flash memory
- 32KB host processor SRAM
- 5 Digital I/Os compatible with Arduino MKR series boards
- 2MB on-board serial flash
- 48MHz system clock
- 6 axis motion sensor
- Digital microphone
An interactive workshop, "Accelerating your Edge Applications with Syntiant's TinyML Board," will be held Thursday, September 30 at noon PDT during Edge Impulse's Imagine conference.