Ultra-low Power, Latency and Cost chips for AI Edge Inference Applications.

Blumind is bringing machine-learning inferencing to the Far Edge, placing it on devices and sensors in all environments. Future applications in Edge AI such as IoT, robotics, Smart Mobility, Smart Home and Smart City will be crippled by the power and latency constraints of current digital technologies. Blumind’s patented analog semiconductor inferencing engine slashes power consumption, latency and silicon area all by orders of magnitude versus digital approaches.

Blumind's first product targets processing of time series and audio data in under 5uW. Future chips will scale up to target computer vision and larger workloads. 

Blumind's total solution includes neural network models, training environment, reference designs and responsive customer support.