Abstract

In this article, we use a convolutional autoencoder neural network to reduce data dimensioning and rebuild soliton dynamics in a passively mode-locked fiber laser. Based on the particle characteristic in double solitons and triple solitons interactions, we found that there is a strict correspondence between the number of minimum compression parameters and the number of independent parameters of soliton interaction. This shows that our network effectively coarsens the high-dimensional data in nonlinear systems. Our work not only introduces new prospects for the laser self-optimization algorithm, but also brings new insights into the modeling of nonlinear systems and description of soliton interactions.

© 2023 Chinese Laser Press

Automated single cardiomyocyte characterization by nucleus extraction from dynamic holographic images using a fully convolutional neural network

Ezat Ahmadzadeh, Keyvan Jaferzadeh, Seokjoo Shin, and Inkyu Moon
Biomed. Opt. Express 11(3) 1501-1516 (2020)

Deep neural network for modeling soliton dynamics in the mode-locked laser

Yin Fang, Hao-Bin Han, Wen-Bo Bo, Wei Liu, Ben-Hai Wang, Yue-Yue Wang, and Chao-Qing Dai
Opt. Lett. 48(3) 779-782 (2023)

Distributed Brillouin frequency shift extraction via a convolutional neural network

Yiqing Chang, Hao Wu, Can Zhao, Li Shen, Songnian Fu, and Ming Tang
Photon. Res. 8(5) 690-697 (2020)

ERA-WGAT: Edge-enhanced residual autoencoder with a window-based graph attention convolutional network for low-dose CT denoising

Han Liu, Peixi Liao, Hu Chen, and Yi Zhang
Biomed. Opt. Express 13(11) 5775-5793 (2022)

High-generalization deep sparse pattern reconstruction: feature extraction of speckles using self-attention armed convolutional neural networks

Yangyundou Wang, Zhaosu Lin, Hao Wang, Chuanfei Hu, Hui Yang, and Min Gu
Opt. Express 29(22) 35702-35711 (2021)