Lightelligence joins incubator with optical AI demo in hand
The startup exchange incubator (STEX) provides networking promotion, travel, and advisory support.
In April of this year Lightelligence announced it had made an optical AI accelerator chip. The chip uses light rather than electrons to perform mathematical operations.
The Lightelligence optical chip demo was used to run MNIST, a machine learning benchmark that recognizes handwritten digits in optical fields. The demo showed that matrix-vector multiplication could be completed by the optical chip 100 times faster than the state-of-the-art electronic chips. The team at Lightelligence have claimed the technology can be scaled to outperform electronic acceleration by many more factors.
Yichen Shen co-founded Lightelligence after studying nanophotonics and machine learning as a Ph.D. student in the lab of Marin Soljacic at MIT. Together with Soljacic and several others, Yichen published a paper in the journal Nature Photonics in 2017 describing a newly discovered way to perform neural-network computations using optical interference.
Lightelligence received about $10.7 million in equity funding in a round led by Baidu Ventures and a group of US semiconductor executives. Baidu is the leading Chinese internet services company.
Related links and articles:
News articles:
Photonics-based AI chips run at attojoule levels
MIT optical AI spin-off raises funds from Baidu
Google invests in photonic processor startup
Nanoscale photonics switch could enable 10-100 Terabit/s data transfer
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
