Nota provides on-device AI solutions that remove the need for any server or cloud computing. We made an innovative move on the development of deep learning model compression technology. We compress the size of AI models small enough to be deployed individually on small edge devices without affecting the performance. So compared to large AI models, our on-device AI technology incurs only 20% of the previous cost and speeds up inference and predictions by 70%. Our compression removes latency, server/network cost, and privacy problems, while still achieving state-of-the-art performance at real-time object detection, identification, and tracking. Clients can now benefit from our stand-alone AI products at a lower cost, faster inference, and no privacy concerns.

Our mission is to democratize AI-based solutions to every aspect of society. Nota’s compression technology allows people who can’t afford high server costs to still benefit from advances in AI, and apply it on even highly sensitive data. Our on-device AI technology will play a significant role in popularizing AI to everyone. We at Nota dream of a world where everyone can benefit from AI in their pockets.


Nota’s AMC (Automatic Model Compression) is a platform that automatically compresses the size of AI models without relying on hand-crafted heuristics. When the user puts in the deep learning model, spec of the target device, and the trained data set, the compression will be solely done by the platform itself and will provide a compressed model within a day. The main feature of our platform is that it automatically compresses the size of the AI model using a variety of lightweight deep learning techniques, including quantization, pruning, knowledge distillation, and filter decomposition. And it can further combine these four techniques to reduce the redundant parameters, required physical memory, computing power, and resource. We’re now using AMC internally to build our on-device vision AI solutions including authentication, video surveillance system, DMS, etc. and to also bring customers’ AI on the edge.