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...

Disgrifiad llawn

Manylion Llyfryddiaeth

Prif Awduron:	Yichen Sun, Mingli Dong, Mingxin Yu, Lidan Lu, Shengjun Liang, Jiabin Xia, Lianqing Zhu
Fformat:	Artigo
Iaith:	Inglês
Cyhoeddwyd:	Taylor & Francis Group 2023-12-01
Cyfres:	International Journal of Optomechatronics
Pynciau:	Diffractive deep neural network Nonlinear functions Optical neural network Rectified linear unit (ReLU)
Mynediad Ar-lein:	https://www.tandfonline.com/doi/10.1080/15599612.2023.2209624
Tagiau:	Ychwanegu Tag Dim Tagiau, Byddwch y cyntaf i dagio'r cofnod hwn!