搜索

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于波动与扩散物理系统的机器学习

陈江芷 杨晨温 任捷

引用本文:
Citation:

基于波动与扩散物理系统的机器学习

陈江芷, 杨晨温, 任捷

Machine learning based on wave and diffusion physical systems

Chen Jiang-Zhi, Yang Chen-Wen, Ren Jie
PDF
HTML
导出引用
  • 物理学在机器学习中的应用以及两者的交叉融合正引起广泛关注, 尤其是在波动系统和扩散系统中. 本文重点关注波动与扩散物理系统和机器学习之间的内在联系以及对机器学习算法和物理实现的推进作用, 综述了波动系统和扩散系统中的机器学习研究, 介绍了部分最新研究成果. 文中首先讨论了监督学习的波动系统实现, 包括神经网络的波动光学实现、量子搜索的波动实现、基于波动系统的递归神经网络以及神经形态的非线性波动计算. 接着, 文中继续讨论了受扩散系统启发的机器学习算法, 如基于扩散动力学的分类算法, 基于热扩散的数据挖掘和信息过滤, 以及基于群体扩散的搜索优化等. 波动系统以其天然的并行性、高效、低能耗等优势, 通过丰富的波动力学和波动物理现象进行计算或算法模拟, 正成为机器学习的新型物理载体. 扩散系统中的物理机制可以启发构建高效的机器学习算法, 用于复杂系统和物理学研究中的分类、优化等问题. 期望通过对波动、扩散物理系统与机器学习内在联系的讨论, 能够为开发物理启发的新算法和硬件实现甚至软硬一体化带来抛砖引玉的启示.
    Recently, the application of physics to machine learning and the interdisciplinary convergence of the two have attracted wide attention. This paper focuses on exploring the internal relationship between physical systems and machine learning, and also on promoting machine learning algorithm and physical implementation. We summarize the researches of machine learning in wave systems and diffusion systems, and introduce some of the latest research results. We first discuss the realization of supervised learning for wave systems, including the wave optics realization of neural networks, the wave realization of quantum search, the recurrent neural networks based on wave systems, and the nonlinear wave computation of neural morphology. Then, we discuss the machine learning algorithms inspired by diffusion systems, such as the classification algorithm based on diffusion dynamics, data mining and information filtering based on thermal diffusion, searching for optimization based on population diffusion, etc. The physical mechanism of diffusion system can inspire the construction of efficient machine learning algorithms for the classification and optimization of complex systems and physics research, which may create a new vision for the development of physics inspired algorithms and hardware implementation, and even the integration of software and hardware.
      通信作者: 任捷, xonics@tongji.edu.cn
    • 基金项目: 国家自然科学基金 (批准号: 11935010, 11775159)、上海市自然科学基金 (批准号: 18JC1410900)、上海市特殊人工微结构材料与技术重点实验室项目和中央高校基本科研业务费专项资金资助的课题
      Corresponding author: Ren Jie, xonics@tongji.edu.cn
    • Funds: Project supported by the National Natural Science Foundation of China (Grant Nos. 11935010, 11775159), the Natural Science Foundation of Shanghai Science and Technology Committee, China (Grant No. 18JC1410900), the Opening Project of Shanghai Key Laboratory of Special Artificial Microstructure Materials and Technology, China, and the Fundamental Research Funds for the Central Universities, China
    [1]

    Eslami S M A, Jimenez R D, Besse F, et al. 2018 Science 360 1204Google Scholar

    [2]

    Mikolov T, Karafiát M, Burget L, Černocký J, Khudanpur S 2010 11th Annual Conference of the International-Speech-Communication-Association Makuhari, Japan, September 26−30, 2010 pp1045−1048

    [3]

    Krizhevsky A, Sutskever I, Hinton G E 2012 Advances in Neural Information Processing Systems 25 1097

    [4]

    Liakos K G, Busato P, Moshou D, Pearson S, Bochtis D 2018 Sensors 18 2674Google Scholar

    [5]

    Carleo G, Cirac I, Cranmer K, Daudet L, Schuld M, Tishby N, Vogt-Maranto L, Zdeborov'a L 2019 Rev. Mod. Phys. 91 045002Google Scholar

    [6]

    Wetzstein G, Ozcan A, Gigan S, Fan S, Englund D, Solja J M, Denz C, Miller D, Psaltis D 2020 Nature 588 39

    [7]

    Miller D A 2019 Adv. Opt. Photonics 11 679Google Scholar

    [8]

    Graves A, Wayne G, Reynolds M, Harley T, Danihelka I, Grabska-Barwińska A, Colmenarejo S G, Grefenstette E, Ramalho T, Agapiou J 2016 Nature 538 471Google Scholar

    [9]

    Brunner D, Soriano M C, Mirasso C R, Fischer I 2013 Nat. Commun. 4 1364Google Scholar

    [10]

    Mehta P, Bukov M, Wang C H, Day A G, Richardson C, Fisher C K, Schwab D 2019 Phys. Rep. 810 1Google Scholar

    [11]

    Sarantoglou G, Skontranis M, Bogris A, Mesaritakis C 2020 2020 Optical Fiber Communications Conference and Exhibition (OFC) San Diego, CA, USA, March 8−12, 2020 p3

    [12]

    Feldmann J, Youngblood N, Wright C D, Bhaskaran H, Pernice W H P 2019 Nature 569 208Google Scholar

    [13]

    Hornik K, Stinchcombe M, White H 1989 IEEE Trans. Neural Networks 2 359Google Scholar

    [14]

    Hopfield J J 1982 PNAS 79 2554Google Scholar

    [15]

    Farhat N, Psaltis D, Prata A, Paek E 1985 Appl. Opt. 24 10 1469

    [16]

    MacQueen J B 1967 Proceedings of the fifth Berkeley Symposium on Mathematical Statistics and Probability (Vol. 1) (California: University of California Press) pp281−297

    [17]

    Dempster A P, Laird N M, Rubin D B 1977 J. R. Stat. Soc. Ser. B-Stat. Methodol. 39 1

    [18]

    Jolliffe I T 1986 Principal Component Analysis (New York: Springer) pp129−155

    [19]

    Roweis S T, Saul L K 2000 Science 290 2323Google Scholar

    [20]

    Tenenbaum J B, De Silva V, Langford J C 2000 Science 290 2319Google Scholar

    [21]

    Long Y, Ren J, Chen H 2020 Phys. Rev. Lett. 124 18 185501Google Scholar

    [22]

    Chung F, Yau S T 2000 J. Comb. Theory Ser. A 91 191Google Scholar

    [23]

    Jiao S, Gao Y, Feng J, Lei T, Yuan X 2020 Opt. Express 28 3 3717Google Scholar

    [24]

    Miller D 2013 Photonics Res. 1 1Google Scholar

    [25]

    Shen Y, Harris N C, Skirlo S, Prabhu M, Baehr-Jones T, Hochberg M, Sun X, Zhao S, Larochelle H, Englund D, Soljačić M 2017 Nat. Photonics 11 441Google Scholar

    [26]

    Chakraborty I, Saha G, Roy K 2019 Phys. Rev. Appl. 11 014063Google Scholar

    [27]

    Chang J, Sitzmann V, Dun X, Heidrich W, Wetzstein G 2018 Sci Rep 8 12324

    [28]

    Zuo Y, Li B, Zhao Y, Jiang Y, Chen Y C, Chen P, Jo G B, Liu J, Du S 2019 Optica 6 1132Google Scholar

    [29]

    Lin X, Rivenson Y, Yardimci N T, Veli M, Luo Y, Jarrahi M, Ozcan A 2018 Science 361 1004Google Scholar

    [30]

    Qian C, Lin X, Lin X, Xu J, Sun Y, Li E, Zhang B, Chen H 2020 Light-Sci. Appl. 9 59Google Scholar

    [31]

    Zhou T, Fang L, Yan T, Wu J, Li Y, Fan J, Wu H, Lin X, Dai Q 2020 Photonics Res. 8 940Google Scholar

    [32]

    Dun X, Ikoma H, Wetzstein G, Wang Z, Cheng X, Peng Y F 2020 Optica 7 913Google Scholar

    [33]

    Weng J, Ding Y, Hu C, Zhu X F, Liang B, Yang J, Cheng J 2020 Nat. Commun. 11 6309Google Scholar

    [34]

    Yan T, Wu J, Zhou T, Xie H, Xu F, Fan J, Fang L, Lin X, Dai Q 2019 Phys. Rev. Lett. 123 2 023901Google Scholar

    [35]

    Zangeneh-Nejad F, Sounas D L, Alù A, Fleury R 2021 Nat. Rev. Mater. 6 207Google Scholar

    [36]

    Zuo S Y, Wei Q, Cheng Y, Liu X J 2017 Appl. Phys. Lett. 110 011904Google Scholar

    [37]

    Zuo S Y, Tian Y, Wei Q, Cheng Y, Liu X J 2017 J. Appl. Phys. 123 091704Google Scholar

    [38]

    Zuo S, Wei Q, Tian Y, Cheng Y, Liu X 2018 Sci Rep 8 10103Google Scholar

    [39]

    Zangeneh-Nejad F, Fleury R 2018 New J. Phys. 20 073001Google Scholar

    [40]

    Yang C, Liu T, Zhu J, Ren J, Chen H 2021 Phys. Rev. Appl. 15 044040Google Scholar

    [41]

    Hughes T, Williamson I A D, Minkov M, Fan S 2019 Sci. Adv. 5 eaay6946Google Scholar

    [42]

    Romera M, Talatchian P, Tsunegi S, Abreu Araujo F, Cros V, Bortolotti P, Trastoy J, Yakushiji K, Fukushima A, Kubota H, Yuasa S, Ernoult M, Vodenicarevic D, Hirtzlin T, Locatelli N, Querlioz D, Grollier J 2018 Nature 563 230Google Scholar

    [43]

    Khoram E, Chen A, Liu D, Ying L, Wang Q, Yuan M, Yu Z 2019 Photonics Res. 7 823Google Scholar

    [44]

    Zhao H 2021 Sci. China-Phys. Mech. Astron. 64 270511Google Scholar

    [45]

    Ren J, Wang W X, Li B, Lai Y C 2010 Phys. Rev. Lett. 104 058701Google Scholar

    [46]

    Marcucci G, Pierangeli D, Conti C 2020 Phys. Rev. Lett. 125 093901Google Scholar

    [47]

    Jaeger H 2001 GMD-Report 148, German National Research Institute for Computer Science

    [48]

    Maass W, Natschläger T, Markram H 2002 Neural Comput 14 2531Google Scholar

    [49]

    Silva N A, Ferreira T D, Guerreiro A 2021 New J. Phys. 23 023013Google Scholar

    [50]

    Nadler B, Lafon S, Coifman R, Kevrekidis I 2005 Appl. Comput. Harmon. Anal. 21 113Google Scholar

    [51]

    Coifman R R, Lafon S, Lee A B, Maggioni M, Nadler B, Warner F, Zucker S W 2005 Proc. Natl. Acad. Sci. U.S.A. 102 7426Google Scholar

    [52]

    Rodriguez-Nieva J, Scheurer M 2018 Nat. Phys. 15 790

    [53]

    Scheurer M S, Slager R J 2020 Phys. Rev. Lett. 124 226401Google Scholar

    [54]

    Lustig E, Yair O, Talmon R, Segev M 2020 Phys. Rev. Lett. 125 12 127401Google Scholar

    [55]

    Lidiak A, Gong Z X 2020 Phys. Rev. Lett. 125 225701Google Scholar

    [56]

    Che Y, Gneiting C, Liu T, Nori F 2020 Phys. Rev. B 102 134213Google Scholar

    [57]

    Zhang Y, Blattner M, Yu Y 2007 Phys. Rev. Lett. 99 154301Google Scholar

    [58]

    Ren J, Zhou T, Zhang Y 2008 EPL 82 58007Google Scholar

    [59]

    Oganov A, Pickard C, Zhu Q, Needs R 2019 Nat. Rev. Mater. 4 331Google Scholar

    [60]

    Schmidt J, Marques M, Botti S, Marques M 2019 NPJ Comput. Mater. 5 83Google Scholar

    [61]

    Zhang L, Wang Y, Lü J, Ma Y 2017 Nat. Rev. Mater. 2 17005Google Scholar

    [62]

    Pickard C J, Needs R J 2011 J. Phys. Condens. Matter 23 053201Google Scholar

    [63]

    Eberhart R, Kennedy J MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science, Nagoya, Japan, October 4–6 1995 pp39−43

    [64]

    Wang Y, Lü J, Zhu L, Ma Y 2010 Phys. Rev. B 82 094116Google Scholar

    [65]

    Wang Y, Lü J, Zhu L, Ma Y 2012 Comput. Phys. Commun. 183 2063Google Scholar

    [66]

    Wang Y, Lü J, Zhu L, Lu S, Yin K, Li Q, Wang H, Zhang L, Ma Y 2015 J. Phys. Condens. Matter 27 20 203203Google Scholar

    [67]

    Wang H, Wang Y, Lü J, Li Q, Zhang L, Ma Y 2016 Comput. Mater. Sci. 112 406Google Scholar

    [68]

    Tong Q, Lv J, Gao P, Wang Y 2019 Chin. Phys. B 28 106105Google Scholar

    [69]

    Gao Z B, Dong X, Li N B, Ren J 2017 Nano Lett. 17 772Google Scholar

    [70]

    Yan S, Wang Y, Gao Z, Long Y, Ren J 2021 Chin. Phys. Lett. 38 027301Google Scholar

    [71]

    Geodecker S 2004 J. Chem. Phys. 120 9911Google Scholar

    [72]

    王磊, 刘金国 2021 物理 50 69Google Scholar

    Wang L, Liu J G 2021 Physics 50 69Google Scholar

    [73]

    Long Y, Ren J, Li Y, Chen H 2019 Appl. Phys. Lett. 114 181105Google Scholar

    [74]

    Tan Y T, Wang L Q, Wang Z, Peng J, Ren J 2021 Chin. Phys. B 30 036301Google Scholar

    [75]

    Miller D 2017 J. Lightwave Technol. 35 346Google Scholar

  • 图 1  (a) 监督学习与无监督学习; (b) 一个单隐藏层神经网络的基本结构, 各层神经元根据权重系数相互连接; (c)利用无监督学习进行社交网络分析

    Fig. 1.  (a) Supervised learning and unsupervised learning; (b) the structure of a single hidden-layer neural network, where neurons are connected by weight coefficients; (c) unsupervised learning can be applied in social network analysis.

    图 2  波在不同介质中的传播以及相应的线性矩阵运算 (a) 传统光学4f系统在傅里叶空间中实现乘法, 对应于在原空间中的卷积. 两个透镜分别实现傅里叶变换和傅里叶逆变换, 散射层对应于核矩阵, 场与薄散射层的相互作用相当于与对角矩阵的乘积; (b) 改进后的4f系统可以用光栅多次复制输入场, 并用不同的核矩阵进行卷积; (c) 通过类似4f的系统可以实现矢量-矩阵乘法, 实现一维行向量与稠密矩阵相乘, 得到一位列向量[6]

    Fig. 2.  Wave propagation through different media and the corresponding linear matrix operations: (a) A traditional optical 4f system realizes multiplication in Fourier space, which corresponds to the convolution in the original space; (b) modified 4f systems can copy the input field with a grating and use different kernels for convolution; (c) a 4f-type system can implement the vector–matrix multiplication[6].

    图 3  (a) 基于相干光和全光学矩阵乘法的硅光子神经形态电路可用于实现元音分类[25]; (b) 基于波分复用(WDM)的分层结构构成的全光脉冲神经网络, 能够实现图像和语言识别[12]; (c) 改进的光学4f系统实现卷积神经网络, 提高图像分类性能[27]; (d) 全光衍射深度神经网络实现数字分类[29]; (e) 光学衍射元件与图像处理算法端对端协同设计[32]

    Fig. 3.  (a) Nanophotonic circuits based on coherent light and all-optical matrix multiplication is capable for vowel recognition[25]; (b) image and language recognition are achieved by an all-optical spiking neural networking with wavelength division multiplexing (WDM)[12]; (c) a design for an optical convolutional layer using a modified optical 4f system[27]; (d) an all-optical diffractive deep neural network that implements the digit classification[29]; (e) end-to-end learning paradigms of diffractive optics and processing algorithms[32].

    图 4  (a) 基于声学超构神经网络的被动目标识别[33]; (b) 利用声表面波系统实现量子搜索算法, 实现与量子逻辑门相似的操作[40]

    Fig. 4.  (a) Passive object recognition with acoustic meta-neural-network[33]; (b) realize quantum search algorithm with acoustic system, achieving operations similar to quantum logic gates[40].

    图 5  标准RNN和波物理的对比 (a)具有离散的输入、输出序列的RNN的更新过程; (b) 具有连续输入、输出序列的波动系统系统的更新过程[41]

    Fig. 5.  Comparison of a standard RNN and a wave system: (a) The update process of an standard RNN with discrete input and output sequence; (b) the update process of a wave-based physical system with continuous input and output sequence[41].

    图 6  神经形态的非线性波动网络 (a) 单波层前馈网络(SWFN)包含编码层、储蓄层和读出层, 其中波按照非线性偏微分方程演化; (b) 偏差$ {\psi }_{b} $的演化、波的演化以及近似计算一维函数$ y={\rm{sin}}\left({\text{π}}x\right)/\left({\text{π}}x\right) $的结果; (c) SWFN用于学习鲍鱼数据集; (d) 用孤子训练通用的布尔逻辑门[46]

    Fig. 6.  Neuromorphic computing by nonlinear waves: (a) Single wave-layer feed forward neural network (SWFN) with input layer, reservoir and readout layer, where the wave evolves according to a nonlinear partial differential equation; (b) the bias and wave evolution and results of learning the function $ y={\rm{sin}}\left({\text{π}}x\right)/\left({\text{π}}x\right) $; (c) results of learning the abalone dataset; (d) training a universal logic gates by soliton gases[46].

    图 7  利用扩散映射实现典型声子系统中的流形聚类 (a) 流形空间降维; (b) 流形空间的样本数据分布与势能绘景; (c) 流形空间的扩散与凝聚, 稳态显示出天然的聚类; (d)随机耦合的无序Su-Schrieffer-Heeger(SSH)声子链; (e) 无序非晶态声子的拓扑分类; (f) 一维非厄米声子链; (g) 高阶拓扑声子[21]

    Fig. 7.  Diffusion mapping in typical phononic systems to realize manifold clustering: (a) Dimension reduction in manifold space; (b) the probability distribution of samples and the effective landscape; (c) along with evolution, the samples diffuse and finally concentrate on positions with minimum local potentials, which indicates the clustering; (d)–(g) applications in disordered photonic SSH chain, amorphous topological phononics, 1D non-Hermitian phononic chain, high-order topological phononics[21].

    图 8  基于扩散映射的无监督学习方法适用于解决不同物理系统中的拓扑分类问题 (a) 一维XY模型拓扑序的检测[52]; (b) 扩散映射能够不借助边缘态, 识别Haldane模型描述的拓扑相变点[54]; (c) 量子系统中的扩散映射算法, 能够无监督地识别$ {\mathbb{Z}}_{3} $横场伊辛模型的量子相[55]

    Fig. 8.  The unsupervised learning with diffusion map is applied to solve topology identification in different physical systems: (a) Identifying the topological order in 1-dimensional XY model[52]; (b) detection of the phase transition for the Haldane model without the edge states[54]; (c) diffusion maps in learning quantum phases with a $ {\mathbb{Z}}_{3} $ transverse field Ising model[55].

    图 9  标号图表明6个点(项目)之间的连接关系, 右侧是对应的权重矩阵和邻接矩阵

    Fig. 9.  Labelled graphs show the connection of 6 points (items), and the corresponding degree matrix and adjacency matrix are on the right side.

    图 10  (a) 全局及局部粒子群优化算法示意图; (b) 粒子群优化算法中速度及位置更新示意图[68]; (c) 多目标优化的二维SnSe材料定向设计工作流程图; (d) 室温下(300 K), 二维SnSe材料单层结构的自由能; (e) 图(d) 中第一Pareto前沿(红线)上的四种新型单层结构的三视图, 深灰色和绿色的球分别表示Sn原子和Se原子[70]

    Fig. 10.  (a) The diagram of PSO; (b) The schematic diagram of the velocity and position updates in PSO[68]; (c) workflow of the multi-objective optimization for 2D SnSe materials design; (d) thermopower landscape at room temperature (300 K) versus the free energy of 2D SnSe materials; (e) four 2D SnSe structures on the first Pareto front, where the dark gray and green balls denote Sn and Se atoms, respectively[70].

  • [1]

    Eslami S M A, Jimenez R D, Besse F, et al. 2018 Science 360 1204Google Scholar

    [2]

    Mikolov T, Karafiát M, Burget L, Černocký J, Khudanpur S 2010 11th Annual Conference of the International-Speech-Communication-Association Makuhari, Japan, September 26−30, 2010 pp1045−1048

    [3]

    Krizhevsky A, Sutskever I, Hinton G E 2012 Advances in Neural Information Processing Systems 25 1097

    [4]

    Liakos K G, Busato P, Moshou D, Pearson S, Bochtis D 2018 Sensors 18 2674Google Scholar

    [5]

    Carleo G, Cirac I, Cranmer K, Daudet L, Schuld M, Tishby N, Vogt-Maranto L, Zdeborov'a L 2019 Rev. Mod. Phys. 91 045002Google Scholar

    [6]

    Wetzstein G, Ozcan A, Gigan S, Fan S, Englund D, Solja J M, Denz C, Miller D, Psaltis D 2020 Nature 588 39

    [7]

    Miller D A 2019 Adv. Opt. Photonics 11 679Google Scholar

    [8]

    Graves A, Wayne G, Reynolds M, Harley T, Danihelka I, Grabska-Barwińska A, Colmenarejo S G, Grefenstette E, Ramalho T, Agapiou J 2016 Nature 538 471Google Scholar

    [9]

    Brunner D, Soriano M C, Mirasso C R, Fischer I 2013 Nat. Commun. 4 1364Google Scholar

    [10]

    Mehta P, Bukov M, Wang C H, Day A G, Richardson C, Fisher C K, Schwab D 2019 Phys. Rep. 810 1Google Scholar

    [11]

    Sarantoglou G, Skontranis M, Bogris A, Mesaritakis C 2020 2020 Optical Fiber Communications Conference and Exhibition (OFC) San Diego, CA, USA, March 8−12, 2020 p3

    [12]

    Feldmann J, Youngblood N, Wright C D, Bhaskaran H, Pernice W H P 2019 Nature 569 208Google Scholar

    [13]

    Hornik K, Stinchcombe M, White H 1989 IEEE Trans. Neural Networks 2 359Google Scholar

    [14]

    Hopfield J J 1982 PNAS 79 2554Google Scholar

    [15]

    Farhat N, Psaltis D, Prata A, Paek E 1985 Appl. Opt. 24 10 1469

    [16]

    MacQueen J B 1967 Proceedings of the fifth Berkeley Symposium on Mathematical Statistics and Probability (Vol. 1) (California: University of California Press) pp281−297

    [17]

    Dempster A P, Laird N M, Rubin D B 1977 J. R. Stat. Soc. Ser. B-Stat. Methodol. 39 1

    [18]

    Jolliffe I T 1986 Principal Component Analysis (New York: Springer) pp129−155

    [19]

    Roweis S T, Saul L K 2000 Science 290 2323Google Scholar

    [20]

    Tenenbaum J B, De Silva V, Langford J C 2000 Science 290 2319Google Scholar

    [21]

    Long Y, Ren J, Chen H 2020 Phys. Rev. Lett. 124 18 185501Google Scholar

    [22]

    Chung F, Yau S T 2000 J. Comb. Theory Ser. A 91 191Google Scholar

    [23]

    Jiao S, Gao Y, Feng J, Lei T, Yuan X 2020 Opt. Express 28 3 3717Google Scholar

    [24]

    Miller D 2013 Photonics Res. 1 1Google Scholar

    [25]

    Shen Y, Harris N C, Skirlo S, Prabhu M, Baehr-Jones T, Hochberg M, Sun X, Zhao S, Larochelle H, Englund D, Soljačić M 2017 Nat. Photonics 11 441Google Scholar

    [26]

    Chakraborty I, Saha G, Roy K 2019 Phys. Rev. Appl. 11 014063Google Scholar

    [27]

    Chang J, Sitzmann V, Dun X, Heidrich W, Wetzstein G 2018 Sci Rep 8 12324

    [28]

    Zuo Y, Li B, Zhao Y, Jiang Y, Chen Y C, Chen P, Jo G B, Liu J, Du S 2019 Optica 6 1132Google Scholar

    [29]

    Lin X, Rivenson Y, Yardimci N T, Veli M, Luo Y, Jarrahi M, Ozcan A 2018 Science 361 1004Google Scholar

    [30]

    Qian C, Lin X, Lin X, Xu J, Sun Y, Li E, Zhang B, Chen H 2020 Light-Sci. Appl. 9 59Google Scholar

    [31]

    Zhou T, Fang L, Yan T, Wu J, Li Y, Fan J, Wu H, Lin X, Dai Q 2020 Photonics Res. 8 940Google Scholar

    [32]

    Dun X, Ikoma H, Wetzstein G, Wang Z, Cheng X, Peng Y F 2020 Optica 7 913Google Scholar

    [33]

    Weng J, Ding Y, Hu C, Zhu X F, Liang B, Yang J, Cheng J 2020 Nat. Commun. 11 6309Google Scholar

    [34]

    Yan T, Wu J, Zhou T, Xie H, Xu F, Fan J, Fang L, Lin X, Dai Q 2019 Phys. Rev. Lett. 123 2 023901Google Scholar

    [35]

    Zangeneh-Nejad F, Sounas D L, Alù A, Fleury R 2021 Nat. Rev. Mater. 6 207Google Scholar

    [36]

    Zuo S Y, Wei Q, Cheng Y, Liu X J 2017 Appl. Phys. Lett. 110 011904Google Scholar

    [37]

    Zuo S Y, Tian Y, Wei Q, Cheng Y, Liu X J 2017 J. Appl. Phys. 123 091704Google Scholar

    [38]

    Zuo S, Wei Q, Tian Y, Cheng Y, Liu X 2018 Sci Rep 8 10103Google Scholar

    [39]

    Zangeneh-Nejad F, Fleury R 2018 New J. Phys. 20 073001Google Scholar

    [40]

    Yang C, Liu T, Zhu J, Ren J, Chen H 2021 Phys. Rev. Appl. 15 044040Google Scholar

    [41]

    Hughes T, Williamson I A D, Minkov M, Fan S 2019 Sci. Adv. 5 eaay6946Google Scholar

    [42]

    Romera M, Talatchian P, Tsunegi S, Abreu Araujo F, Cros V, Bortolotti P, Trastoy J, Yakushiji K, Fukushima A, Kubota H, Yuasa S, Ernoult M, Vodenicarevic D, Hirtzlin T, Locatelli N, Querlioz D, Grollier J 2018 Nature 563 230Google Scholar

    [43]

    Khoram E, Chen A, Liu D, Ying L, Wang Q, Yuan M, Yu Z 2019 Photonics Res. 7 823Google Scholar

    [44]

    Zhao H 2021 Sci. China-Phys. Mech. Astron. 64 270511Google Scholar

    [45]

    Ren J, Wang W X, Li B, Lai Y C 2010 Phys. Rev. Lett. 104 058701Google Scholar

    [46]

    Marcucci G, Pierangeli D, Conti C 2020 Phys. Rev. Lett. 125 093901Google Scholar

    [47]

    Jaeger H 2001 GMD-Report 148, German National Research Institute for Computer Science

    [48]

    Maass W, Natschläger T, Markram H 2002 Neural Comput 14 2531Google Scholar

    [49]

    Silva N A, Ferreira T D, Guerreiro A 2021 New J. Phys. 23 023013Google Scholar

    [50]

    Nadler B, Lafon S, Coifman R, Kevrekidis I 2005 Appl. Comput. Harmon. Anal. 21 113Google Scholar

    [51]

    Coifman R R, Lafon S, Lee A B, Maggioni M, Nadler B, Warner F, Zucker S W 2005 Proc. Natl. Acad. Sci. U.S.A. 102 7426Google Scholar

    [52]

    Rodriguez-Nieva J, Scheurer M 2018 Nat. Phys. 15 790

    [53]

    Scheurer M S, Slager R J 2020 Phys. Rev. Lett. 124 226401Google Scholar

    [54]

    Lustig E, Yair O, Talmon R, Segev M 2020 Phys. Rev. Lett. 125 12 127401Google Scholar

    [55]

    Lidiak A, Gong Z X 2020 Phys. Rev. Lett. 125 225701Google Scholar

    [56]

    Che Y, Gneiting C, Liu T, Nori F 2020 Phys. Rev. B 102 134213Google Scholar

    [57]

    Zhang Y, Blattner M, Yu Y 2007 Phys. Rev. Lett. 99 154301Google Scholar

    [58]

    Ren J, Zhou T, Zhang Y 2008 EPL 82 58007Google Scholar

    [59]

    Oganov A, Pickard C, Zhu Q, Needs R 2019 Nat. Rev. Mater. 4 331Google Scholar

    [60]

    Schmidt J, Marques M, Botti S, Marques M 2019 NPJ Comput. Mater. 5 83Google Scholar

    [61]

    Zhang L, Wang Y, Lü J, Ma Y 2017 Nat. Rev. Mater. 2 17005Google Scholar

    [62]

    Pickard C J, Needs R J 2011 J. Phys. Condens. Matter 23 053201Google Scholar

    [63]

    Eberhart R, Kennedy J MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science, Nagoya, Japan, October 4–6 1995 pp39−43

    [64]

    Wang Y, Lü J, Zhu L, Ma Y 2010 Phys. Rev. B 82 094116Google Scholar

    [65]

    Wang Y, Lü J, Zhu L, Ma Y 2012 Comput. Phys. Commun. 183 2063Google Scholar

    [66]

    Wang Y, Lü J, Zhu L, Lu S, Yin K, Li Q, Wang H, Zhang L, Ma Y 2015 J. Phys. Condens. Matter 27 20 203203Google Scholar

    [67]

    Wang H, Wang Y, Lü J, Li Q, Zhang L, Ma Y 2016 Comput. Mater. Sci. 112 406Google Scholar

    [68]

    Tong Q, Lv J, Gao P, Wang Y 2019 Chin. Phys. B 28 106105Google Scholar

    [69]

    Gao Z B, Dong X, Li N B, Ren J 2017 Nano Lett. 17 772Google Scholar

    [70]

    Yan S, Wang Y, Gao Z, Long Y, Ren J 2021 Chin. Phys. Lett. 38 027301Google Scholar

    [71]

    Geodecker S 2004 J. Chem. Phys. 120 9911Google Scholar

    [72]

    王磊, 刘金国 2021 物理 50 69Google Scholar

    Wang L, Liu J G 2021 Physics 50 69Google Scholar

    [73]

    Long Y, Ren J, Li Y, Chen H 2019 Appl. Phys. Lett. 114 181105Google Scholar

    [74]

    Tan Y T, Wang L Q, Wang Z, Peng J, Ren J 2021 Chin. Phys. B 30 036301Google Scholar

    [75]

    Miller D 2017 J. Lightwave Technol. 35 346Google Scholar

  • [1] 张嘉晖. 蛋白质计算中的机器学习. 物理学报, 2024, 73(6): 069301. doi: 10.7498/aps.73.20231618
    [2] 欧阳鑫健, 张岩星, 王之龙, 张锋, 陈韦嘉, 庄园, 揭晓, 刘来君, 王大威. 面向铁电相变的机器学习: 基于图卷积神经网络的分子动力学模拟. 物理学报, 2024, 73(8): 086301. doi: 10.7498/aps.73.20240156
    [3] 罗启睿, 沈一凡, 罗孟波. 高分子塌缩相变和临界吸附相变的计算机模拟和机器学习. 物理学报, 2023, 72(24): 240502. doi: 10.7498/aps.72.20231058
    [4] 应大卫, 张思慧, 邓书金, 武海斌. 基于机器学习的单拍冷原子成像. 物理学报, 2023, 72(14): 144201. doi: 10.7498/aps.72.20230449
    [5] 张逸凡, 任卫, 王伟丽, 丁书剑, 李楠, 常亮, 周倩. 机器学习结合固溶强化模型预测高熵合金硬度. 物理学报, 2023, 72(18): 180701. doi: 10.7498/aps.72.20230646
    [6] 郭唯琛, 艾保全, 贺亮. 机器学习回归不确定性揭示自驱动活性粒子的群集相变. 物理学报, 2023, 72(20): 200701. doi: 10.7498/aps.72.20230896
    [7] 刘烨, 牛赫然, 李兵兵, 马欣华, 崔树旺. 机器学习在宇宙线粒子鉴别中的应用. 物理学报, 2023, 72(14): 140202. doi: 10.7498/aps.72.20230334
    [8] 管星悦, 黄恒焱, 彭华祺, 刘彦航, 李文飞, 王炜. 生物分子模拟中的机器学习方法. 物理学报, 2023, 72(24): 248708. doi: 10.7498/aps.72.20231624
    [9] 万新阳, 章烨辉, 陆帅华, 吴艺蕾, 周跫桦, 王金兰. 机器学习加速搜寻新型双钙钛矿氧化物光催化剂. 物理学报, 2022, 71(17): 177101. doi: 10.7498/aps.71.20220601
    [10] 黎威, 龙连春, 刘静毅, 杨洋. 基于机器学习的无机磁性材料磁性基态分类与磁矩预测. 物理学报, 2022, 71(6): 060202. doi: 10.7498/aps.71.20211625
    [11] 艾飞, 刘志兵, 张远涛. 结合机器学习的大气压介质阻挡放电数值模拟研究. 物理学报, 2022, 71(24): 245201. doi: 10.7498/aps.71.20221555
    [12] 康俊锋, 冯松江, 邹倩, 李艳杰, 丁瑞强, 钟权加. 基于机器学习的非线性局部Lyapunov向量集合预报订正. 物理学报, 2022, 71(8): 080503. doi: 10.7498/aps.71.20212260
    [13] 张嘉伟, 姚鸿博, 张远征, 蒋伟博, 吴永辉, 张亚菊, 敖天勇, 郑海务. 通过机器学习实现基于摩擦纳米发电机的自驱动智能传感及其应用. 物理学报, 2022, 71(7): 078702. doi: 10.7498/aps.71.20211632
    [14] 李策, 杨栋梁, 孙林锋. 基于二维层状材料的神经形态器件研究进展. 物理学报, 2022, 71(21): 218504. doi: 10.7498/aps.71.20221424
    [15] 刘武, 朱成皖, 李昊天, 赵谡玲, 乔泊, 徐征, 宋丹丹. 基于机器学习和器件模拟对Cu(In,Ga)Se2电池中Ga含量梯度的优化分析. 物理学报, 2021, 70(23): 238802. doi: 10.7498/aps.70.20211234
    [16] 林键, 叶梦, 朱家纬, 李晓鹏. 机器学习辅助绝热量子算法设计. 物理学报, 2021, 70(14): 140306. doi: 10.7498/aps.70.20210831
    [17] 杨自欣, 高章然, 孙晓帆, 蔡宏灵, 张凤鸣, 吴小山. 铅基钙钛矿铁电晶体高临界转变温度的机器学习研究. 物理学报, 2019, 68(21): 210502. doi: 10.7498/aps.68.20190942
    [18] 院琳, 杨雪松, 王秉中. 基于经验知识遗传算法优化的神经网络模型实现时间反演信道预测. 物理学报, 2019, 68(17): 170503. doi: 10.7498/aps.68.20190327
    [19] 彭向凯, 吉经纬, 李琳, 任伟, 项静峰, 刘亢亢, 程鹤楠, 张镇, 屈求智, 李唐, 刘亮, 吕德胜. 基于人工神经网络在线学习方法优化磁屏蔽特性参数. 物理学报, 2019, 68(13): 130701. doi: 10.7498/aps.68.20190234
    [20] 赵永平, 王康康. 具有增加删除机制的正则化极端学习机的混沌时间序列预测. 物理学报, 2013, 62(24): 240509. doi: 10.7498/aps.62.240509
计量
  • 文章访问数:  5902
  • PDF下载量:  409
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-05-10
  • 修回日期:  2021-07-01
  • 上网日期:  2021-07-16
  • 刊出日期:  2021-07-20

/

返回文章
返回