Plumerai makes deep learning radically more efficient, enabling inference on small, inexpensive and low-power hardware. Our technology, powering products such as video doorbell and security cameras, enables the deployment of intelligent, battery-powered sensors everywhere. Our people detection AI consistently proves to be the most accurate for edge devices while consuming minimal resources. Our inference engine for Arm Cortex-M is the fastest and smallest in the world. Our Ikva AI accelerator fits in the smallest of FPGAs. 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. We have published state-of-the-art research on binarized neural networks at conferences such as NeurIPS and MLSys. Our team is backed by world-class investors with strong backgrounds in deep learning and with track records of founding multi-billion dollar companies.
Plumerai
Recent Content by Company
Plumerai Wins MLPerf Tiny 1.1 AI Benchmark for Microcontrollers Again
This blog post was originally published at Plumerai’s website. It is reprinted here with the permission of Plumerai. New results show Plumerai leads performance on all Cortex-M platforms, now also on M0/M0+ Last year we presented our MLPerf Tiny 0.7 and MLPerf Tiny 1.0 benchmark scores, showing that our inference engine runs your AI models …
Plumerai Wins MLPerf Tiny 1.1 AI Benchmark for Microcontrollers Again Read More +
Plumerai People Detection AI Now Runs on Espressif ESP32-S3 MCU
This blog post was originally published at Plumerai’s website. It is reprinted here with the permission of Plumerai. Plumerai People Detection AI is now available on Espressif’s ESP32-S3 microcontroller! Trained with more than 30 million images, Plumerai’s AI detects each person in view, even if partially occluded, and tracks up to 20 people across frames. …
Plumerai People Detection AI Now Runs on Espressif ESP32-S3 MCU Read More +
World’s Fastest Inference Engine Now Supports LSTM-based Recurrent Neural Networks
This blog post was originally published at Plumerai’s website. It is reprinted here with the permission of Plumerai. At Plumerai we enable our customers to perform increasingly complex AI tasks on tiny embedded hardware. We recently observed that more and more of such tasks are using recurrent neural networks (RNNs), in particular RNNs using the …
World’s Fastest Inference Engine Now Supports LSTM-based Recurrent Neural Networks Read More +
MLPerf Tiny 1.0 Confirms: Plumerai’s Inference Engine is Again the World’s Fastest
This blog post was originally published at Plumerai’s website. It is reprinted here with the permission of Plumerai. Earlier this year in April we presented our MLPerf Tiny 0.7 benchmark scores, showing that our inference engine runs your AI models faster than any other tool. Today, MLPerf released the Tiny 1.0 scores and Plumerai has …
MLPerf Tiny 1.0 Confirms: Plumerai’s Inference Engine is Again the World’s Fastest Read More +
Plumerai’s People Detection Powers Quividi’s Audience Measurement Platform
We’re happy to report that Quividi adopted our people detection solution for its audience measurement platform. Quividi is a world leader in the domain of measuring audiences for digital displays and retail media. They have over 600 customers analyzing billions of shoppers every month, across tens of thousands of screens. Quividi’s platform measures consumer engagement …
Plumerai’s People Detection Powers Quividi’s Audience Measurement Platform Read More +
Upcoming Webinar Discusses Rapid, Accurate People Detection
On September 7, 2022 at 10:00 am Central Time, Alliance Member companies Plumerai and Texas Instruments will co-deliver the free webinar “Fast and Accurate People Detection Using a Single Arm Core.” From the event page: Plumerai delivers a complete software solution for highly accurate people detection. Their AI models are tiny and fast, running at …
Upcoming Webinar Discusses Rapid, Accurate People Detection Read More +
