top of page

In-sensor intelligence

backBanner_long.png

At echosonic by RECHO AI Inc., we are revolutionizing physical signal interpretation by bringing always-on time-series signal processing and Machine Learning locally inside MEMS sensors enabled by our innovative Reservoir Processing Unit (RPU). 

​

Low-power, low deployment cost and adaptability allow large deployment of real-time automatic decision making solution in IoT infrastructures and battery powered devices.

Applications

Early Applications - Acoustic.png

RPU's benefits

benefits - RPU.png

Our Story

We are a group of young and energetic physicists, computer scientists, mechanical engineers, and data scientists aiming to disrupt the edge AI market. With robust and continuous university collaborations and public-private cooperation, we are bringing the cutting-edge research of deep technology to human-centric machine learning and building a public forum for disseminating computational technologies.

Our Technology

Backed by the university research, echosonic exploits the dynamic mechanisms of MEMS sensors to enrich the signals with characteristic features for learning-based processing. The hardware/software processing pipeline can be deployed to edge sensors, eliminating privacy and security concern, and draws only 10% of power consumption compared to the legacy devices. 

Low power consumption

Exceptional processing speed

Eliminates privacy and security concerns by processing signals internally on sensors​

Benefits

Reduce >90% in training effort and inferencing at ultra-low power

Privacy and security

Exceptional processing speed by avoiding latency in cloud-device data transferring

Press kit

bottom of page