The Dutch founded startup Plumerai designed a radically more efficient computer chip for deep learning purposes such as object recognition on low-power edge devices with the help of Binarized Neural Networks.
Company Niche: Hardware,
Company Type: Startups & Scaleups,
Location: Amsterdam, Netherlands
Plumerai is making deep learning tiny and radically more efficient to enable inference on small, cheap and low-power hardware. The technology powers camera doorbells, security cameras, smart buildings, and makes it possible to embed intelligent, battery-powered sensors everywhere. Plumerai's people detection AI consistently proves to be the most accurate for edge devices while consuming minimal resources. The inference engine for Arm Cortex-M claims to be the fastest and smallest in the world. Production-worthy embedded AI requires a relentless focus on the full AI stack, from collecting and curating data, to training algorithms, model architectures, inference engines, and hardware optimizations. Plumerai has published state-of-the-art research on Binarized Neural Networks at conferences such as NeurIPS and MLSys. The team is backed by world-class investors with strong backgrounds in deep learning and with track records of founding multi-billion dollar companies. The company has offices in London, Amsterdam and Warsaw.