New chip processes 100 billion pixels in 6 nanoseconds for smarter AI

Researchers at Tsinghua University in China have developed a new photonic chip that processes, transmits, and reconstructs images in nanoseconds.

The chip achieves this feat by skipping the optical to electronic data conversion deployed by conventional chips.

Machine vision is an evolving field in which cameras, sensors, and algorithms work in tandem to make sense of the world around them and perform specific tasks. In the past, technology relied on moving this data over long distances, where it can be analyzed and appropriate responses taken and executed.

Leave a Reply

Your email address will not be published. Required fields are marked *