All-Optical Image Identification with Programmable Matrix Transformation
Optics
2021-08-20 v1 Image and Video Processing
Abstract
An optical neural network is proposed and demonstrated with programmable matrix transformation and nonlinear activation function of photodetection (square-law detection). Based on discrete phase-coherent spatial modes, the dimensionality of programmable optical matrix operations is 30~37, which is implemented by spatial light modulators. With this architecture, all-optical classification tasks of handwritten digits, objects and depth images are performed on the same platform with high accuracy. Due to the parallel nature of matrix multiplication, the processing speed of our proposed architecture is potentially as high as7.4T~74T FLOPs per second (with 10~100GHz detector)
Cite
@article{arxiv.2104.02474,
title = {All-Optical Image Identification with Programmable Matrix Transformation},
author = {Shikang Li and Baohua Ni and Xue Feng and Kaiyu Cui and Fang Liu and Wei Zhang and Yidong Huang},
journal= {arXiv preprint arXiv:2104.02474},
year = {2021}
}