Electro-optical Neural Networks based on Time-stretch Method
Signal Processing
2019-09-18 v1 Artificial Intelligence
Optics
Abstract
In this paper, a novel architecture of electro-optical neural networks based on the time-stretch method is proposed and numerically simulated. By stretching time-domain ultrashort pulses, multiplications of large scale weight matrices and vectors can be implemented on light and multiple-layer of feedforward neural network operations can be easily implemented with fiber loops. Via simulation, the performance of a three-layer electro-optical neural network is tested by the handwriting digit recognition task and the accuracy reaches 88% under considerable noise.
Keywords
Cite
@article{arxiv.1909.07788,
title = {Electro-optical Neural Networks based on Time-stretch Method},
author = {Yubin Zang and Minghua Chen and Sigang Yang and Hongwei Chen},
journal= {arXiv preprint arXiv:1909.07788},
year = {2019}
}