Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Co-designed metaoptoelectronic deep learning.

In Optics express

A metaoptical system is co-designed with electronic hardware to implement deep learning image recognition. The optical convolution block includes a reflective metasurface to perform one layer of a deep neural network. The optical and digital components are jointly optimized to perform an image classification task attaining 65% accuracy, which is close to the 66% accuracy of a fully-digital network where the optical block is replaced by a digital convolution layer.

Villegas Burgos Carlos Mauricio, Xiong Pei, Qiu Liangyu, Zhu Yuhao, Vamivakas A Nickolas

2023-Feb-13