Get the latest tech news
Getting an all-optical AI to handle non-linear math
Instead of sensing photons and processing the results, why not process the photons?
“What makes deep neural networks so powerful is that we’re able to map very complicated relationships in data by repeatedly cascading both these linear operations and non-linear thresholding functions between the layers,” Bandyopadhyay says. A group at MIT led by Dirk Englund, a professor who is a co-author of Bandyopadhyay’s study, demonstrated a photonic chip doing matrix multiplication entirely with light in 2017. To solve this problem, Bandyopadhyay and his colleagues designed and built what is likely the world’s first chip that can compute the entire deep neural net, including both linear and non-linear operations, using photons.
Or read this on Hacker News