3.9 Article

Research Progress in Metamaterial Design and Fiber Beam Control Based on Deep Learning br

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Engineering, Electrical & Electronic

Intelligent Single-Cavity Dual-Comb Source With Fast Locking

Guoqing Pu et al.

Summary: By combining the real-time intelligent control module with the memory-aided intelligent searching algorithm, we have demonstrated the first intelligent single-cavity dual-comb source, effectively solving the problem of starting and stabilizing dual-comb mode-locking in a single cavity. The intelligent dual-comb source can switch from continuous wave state to dual-comb mode-locking state within a mean time of only 2.48 seconds and can recover automatically after interruption. The long-term stability of the intelligent dual-comb source is also validated through a 12-hour test in an open environment.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2023)

Article Optics

Real-Time On-Demand Design of Circuit-Analog Plasmonic Stack Metamaterials by Divide-and-Conquer Deep Learning

Jiankai Xiong et al.

Summary: This article presents a divide-and-conquer deep learning model for the design of plasmonic stack metamaterials (PSMs). The model demonstrates significant reduction in prediction error and training parameters in the forward network, supporting powerful inverse design from spectra to PSM structures. Additionally, a flexible tool based on free customer definition is developed for real-time design of metamaterials with various circuit-analog functions.

LASER & PHOTONICS REVIEWS (2023)

Article Optics

Coherent optical neuron control based on reinforcement learning

Jun Zhang et al.

Summary: Optical neural networks utilize optical neurons to achieve complex functions. The proposed deep reinforcement coherent optical neuron control (DRCON) method improves convergence rate and effective number of bits, showing promise for large-scale optical neural network control.

OPTICS LETTERS (2023)

Article Chemistry, Multidisciplinary

Broadband Solar Metamaterial Absorbers Empowered by Transformer-Based Deep Learning

Wei Chen et al.

Summary: This research develops a deep learning model based on metamaterial spectrum transformer (MST) for the powerful design of high-performance broadband solar metamaterial absorbers (SMA). The model divides the optical spectrum of metamaterial into N patches, overcoming the problem of overfitting in traditional deep learning and greatly enhancing the learning capability. A flexible design tool is also developed for real-time on-demand design of metamaterials with various optical functions.

ADVANCED SCIENCE (2023)

Article Optics

Deep reinforcement with spectrum series learning control for a mode-locked fiber laser

Zhan Li et al.

Summary: A spectrum series learning-based model is proposed for mode-locked fiber laser state searching and switching. The model combines deep reinforcement learning and long short-term memory networks to obtain the mode-locked operation search policy. The switch of the mode-locked state is realized by a predictive neural network that controls the pump power. Experimental results show that this new method achieves high efficiency and accuracy in searching and switching mode-locked states.

PHOTONICS RESEARCH (2022)

Article Optics

A Deep Reinforcement Learning Algorithm for Smart Control of Hysteresis Phenomena in a Mode-Locked Fiber Laser

Alexey Kokhanovskiy et al.

Summary: In this study, we applied a double deep Q-learning network algorithm (DDQN) to design a self-starting fiber mode-locked laser and successfully achieved stable mode-locked soliton generation. Compared to static optimization, the algorithm is capable of learning dynamic adjustment strategies for cavity parameters, leading to improved performance.

PHOTONICS (2022)

Article Optics

Ultrafast true-green Ho:ZBLAN fiber laser inspired the TD3 AI

Saiyu Luo et al.

Summary: This study successfully generated picosecond lasers in the true-green spectrum using an artificial intelligence algorithm, extending the application of AI technology into the field of ultrafast photonics.

OPTICS LETTERS (2022)

Article Chemistry, Multidisciplinary

Data-Enhanced Deep Greedy Optimization Algorithm for the On-Demand Inverse Design of TMDC-Cavity Heterojunctions

Zeyu Zhao et al.

Summary: A data-enhanced deep greedy optimization (DEDGO) algorithm is proposed for efficient and on-demand inverse design of multiple TMDC-phonic cavity-integrated heterojunctions. DEDGO integrates the decision theory of reinforcement learning and employs iterative optimization and data enhancement methods, achieving higher accuracy and effectiveness compared to conventional methods.

NANOMATERIALS (2022)

Article Nanoscience & Nanotechnology

Data enhanced iterative few-sample learning algorithm-based inverse design of 2D programmable chiral metamaterials

Zeyu Zhao et al.

Summary: This study proposes a data enhanced iterative few-sample (DEIFS) algorithm for accurate and efficient inverse design of multi-shaped 2D chiral metamaterials. By adding new functionality and performing data enhancement and iterations, the algorithm achieves accurate inverse design with smaller amounts of data, reducing the dependence on simulated spectra. Furthermore, the algorithm demonstrates potential value in optical coding and information processing applications.

NANOPHOTONICS (2022)

Review Physics, Multidisciplinary

Short-pulsed Raman fiber laser and its dynamics

Jun Liu et al.

Summary: Short-pulsed Raman fiber lasers provide flexible laser emissions for various applications and are an excellent platform to study nonlinear pulse dynamics behaviors. Despite significant advancements in the past few decades, the output performance of these lasers still needs improvement.

SCIENCE CHINA-PHYSICS MECHANICS & ASTRONOMY (2021)

Article Nanoscience & Nanotechnology

Expedited circular dichroism prediction and engineering in two-dimensional diffractive chiral metamaterials leveraging a powerful model-agnostic data enhancement algorithm

Shiyin Du et al.

Summary: The MADE algorithm efficiently investigates the CD properties of 2D chiral metamaterials with different parameters, utilizing less data and training data, and applying machine learning models. It provides a fast, accurate, and data-friendly method for evaluating optical chirality in 2D metamaterials.

NANOPHOTONICS (2021)

Article Optics

Monte Carlo simulation fused with target distribution modeling via deep reinforcement learning for automatic high-efficiency photon distribution estimation

Jianhui Ma et al.

Summary: This work aims to develop an automatic scatter estimation framework for efficient photon distribution estimation, utilizing GPU-based MC simulations and an over-relaxation algorithm combined with deep reinforcement learning. The proposed method can rapidly and accurately estimate scatter signals with a large range of photon numbers, achieving superior performance in terms of structural similarity, peak signal-to-noise ratio, and relative absolute error.

PHOTONICS RESEARCH (2021)

Article Optics

Integrating deep learning to achieve phase compensation for free-space orbital-angular-momentum-encoded quantum key distribution under atmospheric turbulence

Xingyu Wang et al.

Summary: This paper presents an adaptive compensation method using deep learning technology to improve the performance of OAM-encoded QKD schemes and designs a QKD scheme with real-time phase correction capability to ensure information security.

PHOTONICS RESEARCH (2021)

Article Optics

Intelligent coding metasurface holograms by physics-assisted unsupervised generative adversarial network

Che Liu et al.

Summary: Intelligent coding metasurface is capable of manipulating electromagnetic waves and associating digital information simultaneously, showing promising applications. The proposed physics-driven variational auto-encoder cGAN, based on unsupervised conditional generative adversarial networks, offers an efficient approach to design intelligent coding metasurface holograms.

PHOTONICS RESEARCH (2021)

Article Optics

Realizing transmitted metasurface cloak by a tandem neural network

Zheng Zhen et al.

Summary: Being invisible has been a dream for centuries, and recent breakthroughs in technology have led to the development of a transmitted metasurface cloak, opening up new possibilities for transparent invisibility.

PHOTONICS RESEARCH (2021)

Article Optics

Achieving efficient inverse design of low-dimensional heterostructures based on a vigorous scalable multi-task learning network

Shiyin Du et al.

Summary: A scalable multi-task learning (SMTL) model is proposed for efficient inverse design of low-dimensional heterostructures and prediction of their optical response. Two key algorithms that ensure the SMTL network can handle different tasks with unbiased datasets and capture the impact of nanostructures' dimensions on optical absorption are implemented. This work confirms the multi-structure inverse design functionality of SMTL and establishes a framework for heterostructures in the field of nanophotonics.

OPTICS EXPRESS (2021)

Article Multidisciplinary Sciences

Phase-to-pattern inverse design paradigm for fast realization of functional metasurfaces via transfer learning

Ruichao Zhu et al.

Summary: This paper introduces a fast and accurate method for designing functional metasurfaces based on transfer learning, which can generate metasurface patterns monolithically for specific functions with high design accuracy. The proposed inverse design paradigm provides a efficient way for functional metasurface design and can be applied to establish a meta-atom library with full phase span.

NATURE COMMUNICATIONS (2021)

Article Optics

Low-latency deep-reinforcement learning algorithm for ultrafast fiber lasers

Qiuquan Yan et al.

Summary: Machine learning is increasingly applied in the field of ultrafast photonics. This paper presents a deep-reinforcement learning algorithm for automatic mode-locked operation in a saturable absorber-based ultrafast fiber laser (UFL). Two experiments were conducted to verify the effectiveness and robustness of the algorithm, which lays the foundation for remote maintenance and centralized control of UFLs.

PHOTONICS RESEARCH (2021)

Article Optics

Automated Design Study of Guided-Mode Resonance Filters Working at Terahertz Frequencies

Shao Tianyu et al.

Summary: In this study, an automated design method for terahertz GMR filters is proposed, which utilizes CST under the PSO framework to obtain parameters for a silicon grating working at 0.65 THz and a more complex metasurface grating working at 0.6 THz. The simulated electric field distributions verify the GMR feature of the resonances realized in the gratings. Compared with the traditional RCWA method, our approach achieves high quality factor resonance and can handle complex structures effectively.

CHINESE JOURNAL OF LASERS-ZHONGGUO JIGUANG (2021)

Article Optics

Intelligent algorithms: new avenues for designing nanophotonic devices [Invited]

Lifeng Ma et al.

Summary: Intelligent algorithms have shown vigorous development in the field of nanophotonic devices, breaking the restrictions of traditional methods and predicting novel configurations. They are universal and efficient for different materials, structures, modes, wavelengths, etc.

CHINESE OPTICS LETTERS (2021)

Review Computer Science, Information Systems

A review on genetic algorithm: past, present, and future

Sourabh Katoch et al.

Summary: This paper discusses recent advances in genetic algorithms, analyzing selected algorithms of interest in the research community. It helps new and demanding researchers gain a broader understanding of genetic algorithms. The review covers well-known algorithms, genetic operators, research domains, and future research directions in genetic algorithms.

MULTIMEDIA TOOLS AND APPLICATIONS (2021)

Article Engineering, Electrical & Electronic

Genetic Algorithm-Based Fast Real-Time Automatic Mode-Locked Fiber Laser

Guoqing Pu et al.

IEEE PHOTONICS TECHNOLOGY LETTERS (2020)

Article Chemistry, Physical

Deep learning approach based on dimensionality reduction for designing electromagnetic nanostructures

Yashar Kiarashinejad et al.

NPJ COMPUTATIONAL MATERIALS (2020)

Editorial Material Optics

Toward a self-driving ultrafast fiber laser

Fanchao Meng et al.

LIGHT-SCIENCE & APPLICATIONS (2020)

Article Optics

Towards visible-wavelength passively mode-locked lasers in all-fibre format

Jinhai Zou et al.

LIGHT-SCIENCE & APPLICATIONS (2020)

Article Computer Science, Hardware & Architecture

Generative Adversarial Networks

Ian Goodfellow et al.

COMMUNICATIONS OF THE ACM (2020)

Review Automation & Control Systems

Deep Reinforcement Learning for Multiagent Systems: A Review of Challenges, Solutions, and Applications

Thanh Thi Nguyen et al.

IEEE TRANSACTIONS ON CYBERNETICS (2020)

Review Chemistry, Multidisciplinary

Plasmonic metamaterials for chiral sensing applications

Yoon Young Lee et al.

NANOSCALE (2020)

Article Automation & Control Systems

Knowledge Discovery in Nanophotonics Using Geometric Deep Learning

Yashar Kiarashinejad et al.

ADVANCED INTELLIGENT SYSTEMS (2020)

Article Chemistry, Physical

Bandgap prediction by deep learning in configurationally hybridized graphene and boron nitride

Yuan Dong et al.

NPJ COMPUTATIONAL MATERIALS (2019)

Article Geochemistry & Geophysics

Deep learning electromagnetic inversion with convolutional neural networks

Vladimir Puzyrev

GEOPHYSICAL JOURNAL INTERNATIONAL (2019)

Article Nanoscience & Nanotechnology

Migrating Knowledge between Physical Scenarios Based on Artificial Neural Networks

Yurui Qu et al.

ACS PHOTONICS (2019)

Article Chemistry, Multidisciplinary

Free-Form Diffractive Metagrating Design Based on Generative Adversarial Networks

Jiaqi Jiang et al.

ACS NANO (2019)

Article Multidisciplinary Sciences

Double-deep Q-learning to increase the efficiency of metasurface holograms

Iman Sajedian et al.

SCIENTIFIC REPORTS (2019)

Article Optics

Deep reinforcement learning for coherent beam combining applications

Henrik Tunnermann et al.

OPTICS EXPRESS (2019)

Article Physics, Multidisciplinary

Self-starting all-fiber PM Er:laser mode locked by a biased nonlinear amplifying loop mirror

Ke Yin et al.

CHINESE PHYSICS B (2019)

Article Materials Science, Multidisciplinary

Deep neural network for plasmonic sensor modeling

Xiaozhong Li et al.

OPTICAL MATERIALS EXPRESS (2019)

Article Chemistry, Multidisciplinary

Deep-Learning-Enabled On-Demand Design of Chiral Metamaterials

Wei Ma et al.

ACS NANO (2018)

Article Physics, Applied

Neural network based design of metagratings

Sandeep Inampudi et al.

APPLIED PHYSICS LETTERS (2018)

Article Engineering, Electrical & Electronic

Bidirectional Red-Light Passively Q-Switched All-Fiber Ring Lasers With Carbon Nanotube Saturable Absorber

Wensong Li et al.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2018)

Article Nanoscience & Nanotechnology

Training Deep Neural Networks for the Inverse Design of Nanophotonic Structures

Dianjing Liu et al.

ACS PHOTONICS (2018)

Article Multidisciplinary Sciences

Nanophotonic particle simulation and inverse design using artificial neural networks

John Peurifoy et al.

SCIENCE ADVANCES (2018)

Article Optics

Plasmonic nanostructure design and characterization via Deep Learning

Itzik Malkiel et al.

LIGHT-SCIENCE & APPLICATIONS (2018)

Article Optics

Polarization-multiplexed, dual-comb all-fiber mode-locked laser

Xin Zhao et al.

PHOTONICS RESEARCH (2018)

Review Optics

Inverse design in nanophotonics

Sean Molesky et al.

NATURE PHOTONICS (2018)

Article Multidisciplinary Sciences

Towards 'smart lasers': self-optimisation of an ultrafast pulse source using a genetic algorithm

R. I. Woodward et al.

SCIENTIFIC REPORTS (2016)

Article Multidisciplinary Sciences

Human-level control through deep reinforcement learning

Volodymyr Mnih et al.

NATURE (2015)

Article Optics

Accurate near-field calculation in the rigorous coupled-wave analysis method

Martin Weismann et al.

JOURNAL OF OPTICS (2015)

Article Engineering, Electrical & Electronic

Extremum-Seeking Control of a Mode-Locked Laser

Steven L. Brunton et al.

IEEE JOURNAL OF QUANTUM ELECTRONICS (2013)

Article Automation & Control Systems

PID control system analysis, design, and technology

KH Ang et al.

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY (2005)

Article Engineering, Electrical & Electronic

A novel dispersive FDTD formulation for modeling transient propagation in chiral metamaterials

A Akyurtlu et al.

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION (2004)

Article Physics, Multidisciplinary

Reversing light with negative refraction

JB Pendry et al.

PHYSICS TODAY (2004)

Article Multidisciplinary Sciences

Observation of the inverse Doppler effect

N Seddon et al.

SCIENCE (2003)

Article Multidisciplinary Sciences

Cerenkov radiation in photonic crystals

C Luo et al.

SCIENCE (2003)

Article Physics, Multidisciplinary

Composite medium with simultaneously negative permeability and permittivity

DR Smith et al.

PHYSICAL REVIEW LETTERS (2000)