Shanghai University Integrates Optical AI Engine on Top of a Regular Image Sensor

University of Shanghai for Science and Technology publishes Nature paper "Nanoprinted high-neuron-density optical linear perceptrons performing near-infrared inference on a CMOS chip" by Elena Goi, Xi Chen, Qiming Zhang, Benjamin P. Cumming, Steffen Schoenhardt, Haitao Luan & Min Gu .

“By employing high-precision 3D nanofabrication technology, we are able to add AI optical elements to industry-standard imaging sensors. This is comparable to putting tailored, task-specific smart glasses on the imaging sensors, which process the incoming optical information before it is even detected,” says Elena Goi, the first author of the published paper. 

By printing the perceptrons directly on CMOS imaging chips, Goi said, it is possible to realise AI optical circuits, which not only outperform current optical methods, but show the potential for application in a wide range of fields from security check, medical diagnostics, automatic driving, satellite image processing, etc.

The AI-enabled sensor is even able to communicate in Morse messages: