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.
Funding Information
  • Beijing Municipal Science and Technology Commission, Adminitrative Commission of Zhongguancun Science Park (Z181100008918011)
  • National Natural Science Foundation of China (61771284)
  • Natural Science Foundation of Beijing Municipality (L182043)

This publication has 34 references indexed in Scilit: