Tiny AI is a paradigm shift in how we approach artificial intelligence, says Plumerai Co-founder and CEO Roeland Nusselder. He says tiny AI allows the embedding of powerful AI capabilities directly into smart home devices, enhancing security and privacy in ways that were once considered unfeasible.
“It’s not about making AI bigger; it’s about making it smarter, more accessible, and more aligned with people’s real-world needs,” Nusselder said.
Plumerai has built an accurate tiny AI solution for smart home cameras, trained with over 30 million images and videos. Internal test comparisons against a leading smart camera, widely regarded as the most accurate among established smart home players, revealed striking results. The leading smart camera’s AI incorrectly identified strangers as household members in 2% of the recorded events, while Plumerai’s familiar face identification made no incorrect identifications.
To achieve features like people detection and familiar face identification, cloud-based AI and, in particular, large language models (LLMs) require vast remote data centres, consume increasing amounts of energy, pose privacy risks, and incur rising costs.
Plumerai’s tiny AI can do all this on the device itself, is cost-effective, chip-agnostic, capable of operating on battery-powered devices, doesn’t clog up bandwidth with huge video uploads, and has minuscule energy requirements. Moreover, it boasts the most accurate on-device tiny AI on the market and offers end-to-end encryption.
The developments come as Plumerai announces a partnership with secure access company Chamberlain Group, whose brands include myQ and LiftMaster.
“Integrating Plumerai’s tiny AI into our smart camera lineup has allowed us to offer advanced AI features on affordable, low-power devices,” said Chamberlain’s Jishnu Kinwar. “This enables us to provide our customers with smarter, more efficient products that deliver high performance without the need for cloud processing.”
