Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2022 Oct 13;13:6048. doi: 10.1038/s41467-022-33877-7

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2022

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Fig. 4 — a The set-up diagram of training. The panel on the left side represents the data flow during training, where W(V), f (∙) are linear and nonlinear operations, respectively. X, Y are the input of the first layer and the output of the last layer, respectively. U and I are the optical input and electrical output of the last layer of AONU, respectively. V is the voltage that controls the weighting. LD, Laser. EDFA, Erbium-Doped Fiber Amplifier. VOA, Variable Optical Attenuator. PC, Polarization Controller. b Introduction of the classification task. Four modes are utilized for simplified classification tasks. The classified patterns are represented by 4 × 1 vectors. Black pixel is represented by ′1′ and input, while white is ′0′ and no input. The task is to train the neural network so that all modes are output only at their labeled ports. c The results of the classification task. The insets are the probabilities of each mode output from the four ports. d Introduction of the semantic segmentation task. The input in the dark gray area is set to 0.9 and the output is 1. The input in the light gray area is set to 0.1 and the output is 0. e The results of the semantic segmentation task. The insets are the relative outputs of 16 pixels.