Making Edge AI a Reality
We foresee a world with billions of intelligent devices enabled by Syntiant® Neural Decision Processors™ and Deep Learning AI models that sense, analyze and autonomously act to create a healthier and more sustainable environment for all.
Syntiant solutions can equip, every device, from earbuds and doorbells to automobiles and manufacturing machinery, with powerful deep learning capabilities, enabling real-time data processing and decision making, with near zero latency and at a fraction of the power of traditional solutions.
A New Processor for Deep Learning
Deep learning systems differ dramatically from traditional computing methods. By using at-memory compute and natively processing neural network instructions, Syntiant devices typically deliver 100x the performance when compared to traditional processing technologies. Our solution enables moving larger neural workloads from a high-powered application processor (or even a cloud server) to a low-power, always-on domain while simultaneously increasing responsiveness and battery life.
Turnkey Machine Learning Models
Syntiant's models are specially designed for a variety of edge applications using audio, vision, and sensor data to build intelligence into devices. Syntiant's complete data collection and training toolkit supports training and deploying highly accurate production-quality models that run an order of magnitude faster than open-source solutions. What is more, these models can run on a variety of hardware solutions ranging from Syntiant's own neural decision processors to commonly available CPU and GPU devices.
Always-on Voice (AOV)
Supporting modern voice interfaces like the Amazon Alexa and OK Google as well as custom wake word and commands.
Offering object detection, classification, and tracking in complex environments.
AI for IoT
On-device deep learning for better decisions, extended usage time, and a drastically improved experience.
Applications for the Intelligence of Everything