New Approach Promises Ultra-Low-Power Task-Agnostic Optical Neural Networks for Embedded Vision
A team of scientists from the Chinese University of Hong Kong and the Center for Perceptual and Interactive Intelligence at Shatin have come up with a new approach to delivering ultra-low-power machine vision for embedded cameras — by building a task-agnostic optical neural network that can be fabricated into a viable chip in as little as 15 minutes.
"Unlike conventional metasurfaces or other optical neural network platforms, which typically rely on one-off or costly fabrication schemes and thus face significant barriers to scalability, our method intrinsically supports cost-effective mass production," the researchers, led by professors Shih-Chi Chen and Chaoran Huang explain of the project. "This unique capability bridges the gap between high-precision prototyping and scalable device manufacturing, thereby offering a practical and economical pathway towards the deployment of optical neural networks."
A new approach to manufacturing optical neural networks promises to deliver major gains in on-device machine vision efficiency. (📷:...
Copyright of this story solely belongs to hackster.io. To see the full text click HERE
