A method to improve the computational performance of nonlinear all—optical diffractive deep neural network model

A method to improve the computational performance of nonlinear all—optical diffractive deep neural network model

AbstractTo further improve the computational performance of the diffractive deep neural network (D2NN) model, we use the ReLU function to limit the phase parameters, which effectively solves the problem of vanishing gradient that occurs in the mitigation model. We add various commonly used nonlinear...

Full description

Bibliographic Details
Main Authors: Yichen Sun, Mingli Dong, Mingxin Yu, Lidan Lu, Shengjun Liang, Jiabin Xia, Lianqing Zhu
Format: Article
Language:English
Published: Taylor & Francis Group 2023-12-01
Series:International Journal of Optomechatronics
Subjects:
Diffractive deep neural network
Nonlinear functions
Optical neural network
Rectified linear unit (ReLU)
Online Access:https://www.tandfonline.com/doi/10.1080/15599612.2023.2209624

Internet

https://www.tandfonline.com/doi/10.1080/15599612.2023.2209624

Similar Items