• Chinese Journal of Lasers
  • Vol. 50, Issue 11, 1101007 (2023)
Yihao Luo1, Jun Zhang2, Shiyin Du2, Qiuquan Yan2, Zeyu Zhao2, Zilong Tao2, Tong Zhou1, and Tian Jiang3、*
Author Affiliations
  • 1College of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha 410073, Hunan, China
  • 2Institute for Quantum Information and the State Key Laboratory of High Performance Computing, College of Computer Science and Technology, National University of Defense Technology, Changsha 410073, Hunan, China
  • 3Institute of Quantum Information Science and Technology, College of Science, National University of Defense Technology, Changsha 410073, Hunan, China
  • show less
    DOI: 10.3788/CJL230540 Cite this Article Set citation alerts
    Yihao Luo, Jun Zhang, Shiyin Du, Qiuquan Yan, Zeyu Zhao, Zilong Tao, Tong Zhou, Tian Jiang. Research Progress in Metamaterial Design and Fiber Beam Control Based on Deep Learning[J]. Chinese Journal of Lasers, 2023, 50(11): 1101007 Copy Citation Text show less
    Architecture of multi-layer perceptron network[29]. (a) Network structure; (b) mathematics process of perceptron
    Fig. 1. Architecture of multi-layer perceptron network[29]. (a) Network structure; (b) mathematics process of perceptron
    Simple recurrent neural network and its computational graph
    Fig. 2. Simple recurrent neural network and its computational graph
    Architecture of autoencoder
    Fig. 3. Architecture of autoencoder
    Partition of material parameter space based on dielectric constant and permeability[5]
    Fig. 4. Partition of material parameter space based on dielectric constant and permeability[5]
    Applications of metamaterials in various fields. (a) Optical communication[68]; (b) biomedicine[70]; (c) sensitive detection[69]
    Fig. 5. Applications of metamaterials in various fields. (a) Optical communication[68]; (b) biomedicine[70]; (c) sensitive detection[69]
    Common metamaterial design methods
    Fig. 6. Common metamaterial design methods
    Application of MLP in metamaterial design. (a) Using MLP to design nanoparticle[89]; (b) using MLP series to solve multi-solution problems[90]; (c) optimization and improvement of MLP—SMTL model[34]; (d) optimization and improvement of MLP—DEIFS algorithm[91]
    Fig. 7. Application of MLP in metamaterial design. (a) Using MLP to design nanoparticle[89]; (b) using MLP series to solve multi-solution problems[90]; (c) optimization and improvement of MLP—SMTL model[34]; (d) optimization and improvement of MLP—DEIFS algorithm[91]
    Other deep learning methods for metamaterial design. (a) Using CNN to design binary imaged metasurface devices[92]; (b) using GAN to design metamaterial devices with complex topology[93]; (c) using DDQN to dynamically design device material types and structure parameters[94]; (d) using DEDGO to design a variety of low-dimensional heterostructures[95]; (e) using RNN to design metamaterial devices[18]
    Fig. 8. Other deep learning methods for metamaterial design. (a) Using CNN to design binary imaged metasurface devices[92]; (b) using GAN to design metamaterial devices with complex topology[93]; (c) using DDQN to dynamically design device material types and structure parameters[94]; (d) using DEDGO to design a variety of low-dimensional heterostructures[95]; (e) using RNN to design metamaterial devices[18]
    Basic model of intelligent optimization algorithm in optical system
    Fig. 9. Basic model of intelligent optimization algorithm in optical system
    Intelligent mode-locked laser structures based on different search methods. (a) Experimental structure of self-optimizing mode-locked laser based on genetic algorithm[112]; (b) experimental structure of intelligent mode-locked fiber laser based on HLA algorithm[113]
    Fig. 10. Intelligent mode-locked laser structures based on different search methods. (a) Experimental structure of self-optimizing mode-locked laser based on genetic algorithm[112]; (b) experimental structure of intelligent mode-locked fiber laser based on HLA algorithm[113]
    Intelligent mode-locked laser structures based on different deep reinforcement learning algorithms. (a) Adaptive mode-locked laser model designed using DQN algorithm[115]; (b) automatic mode-locked laser system based on DELAY algorithm[24]; (c) mode-locked laser system based on reinforcement learning and spectral learning[116]; (d) intelligent mode-locked laser architecture based on TD3 algorithm[117]
    Fig. 11. Intelligent mode-locked laser structures based on different deep reinforcement learning algorithms. (a) Adaptive mode-locked laser model designed using DQN algorithm[115]; (b) automatic mode-locked laser system based on DELAY algorithm[24]; (c) mode-locked laser system based on reinforcement learning and spectral learning[116]; (d) intelligent mode-locked laser architecture based on TD3 algorithm[117]
    Control structure of partially coherent optical systems. (a) Coherent beam combination system for 4-beam fiber amplifier based on SPGD algorithm[119]; (b) two-stage phase control system based on deep learning model and SPGD algorithm[120]
    Fig. 12. Control structure of partially coherent optical systems. (a) Coherent beam combination system for 4-beam fiber amplifier based on SPGD algorithm[119]; (b) two-stage phase control system based on deep learning model and SPGD algorithm[120]
    Coherent optical neuron system[123]
    Fig. 13. Coherent optical neuron system[123]
    YearAlgorithm nameMode-locked state search time
    2015EA118~30 min
    2016GA112~30 min
    2017GA102~30 s
    2019HLA1130.22 s least recovery time3.1 s average recovery time
    2021DELAY240.472 s least recovery time1.948 s average recovery time
    2022MDRL1160.2 s least recovery time0.69 s average recovery time
    Table 1. Comparison of different algorithms in mode-locking time
    Yihao Luo, Jun Zhang, Shiyin Du, Qiuquan Yan, Zeyu Zhao, Zilong Tao, Tong Zhou, Tian Jiang. Research Progress in Metamaterial Design and Fiber Beam Control Based on Deep Learning[J]. Chinese Journal of Lasers, 2023, 50(11): 1101007
    Download Citation