Restricted Boltzmann machine: Recent advances and mean-field theory*

被引:39
|
作者
Decelle, Aurelien [1 ,2 ,3 ]
Furtlehner, Cyril [2 ,3 ]
机构
[1] Univ Complutense, Dept Fis Teor 1, Madrid 28040, Spain
[2] Univ Paris Saclay, INRIA Saclay, TAU Team, F-91405 Orsay, France
[3] Univ Paris Saclay, LISN, F-91405 Orsay, France
关键词
restricted Boltzmann machine (RBM); machine learning; statistical physics; STATISTICAL-MECHANICS; NEURAL-NETWORKS; MODEL; STORAGE;
D O I
10.1088/1674-1056/abd160
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
This review deals with restricted Boltzmann machine (RBM) under the light of statistical physics. The RBM is a classical family of machine learning (ML) models which played a central role in the development of deep learning. Viewing it as a spin glass model and exhibiting various links with other models of statistical physics, we gather recent results dealing with mean-field theory in this context. First the functioning of the RBM can be analyzed via the phase diagrams obtained for various statistical ensembles of RBM, leading in particular to identify a compositional phase where a small number of features or modes are combined to form complex patterns. Then we discuss recent works either able to devise mean-field based learning algorithms; either able to reproduce generic aspects of the learning process from some ensemble dynamics equations or/and from linear stability arguments.
引用
收藏
页数:24
相关论文
共 50 条
  • [41] Fermion-boson vertex within dynamical mean-field theory
    van Loon, Erik G. C. P.
    Krien, Friedrich
    Hafermann, Hartmut
    Lichtenstein, Alexander, I
    Katsnelson, Mikhail, I
    PHYSICAL REVIEW B, 2018, 98 (20)
  • [42] Derivation of Hartree's theory for generic mean-field Bose systems
    Lewin, Mathieu
    Phan Thanh Nam
    Rougerie, Nicolas
    ADVANCES IN MATHEMATICS, 2014, 254 : 570 - 621
  • [43] MEAN-FIELD OPTIMAL CONTROL
    Fornasier, Massimo
    Solombrino, Francesco
    ESAIM-CONTROL OPTIMISATION AND CALCULUS OF VARIATIONS, 2014, 20 (04) : 1123 - 1152
  • [44] Schwinger boson approach for the dynamical mean-field theory of the Kondo lattice
    Han, Rulei
    Hu, Danqing
    Wang, Jiangfan
    Yang, Yi-feng
    PHYSICAL REVIEW B, 2021, 104 (24)
  • [45] Mean-field theory for confinement transitions and magnetization plateaux in spin ice
    Powell, Stephen
    JOURNAL OF PHYSICS A-MATHEMATICAL AND THEORETICAL, 2017, 50 (12)
  • [46] Mean-field kinetic theory approach to Langmuir evaporation of polyatomic liquids
    Busuioc, Sergiu
    Gibelli, Livio
    PHYSICS OF FLUIDS, 2020, 32 (09)
  • [47] Embedding dynamical mean-field theory for superconductivity in layered materials and heterostructures
    Petocchi, Francesco
    Capone, Massimo
    PHYSICAL REVIEW B, 2016, 93 (23)
  • [48] Mean-field theory of a plastic network of integrate-and-fire neurons
    Chen, Chun-Chung
    Jasnow, David
    PHYSICAL REVIEW E, 2010, 81 (01):
  • [49] Free energy equivalence between mean-field models and nonsparsely diluted mean-field models
    Okuyama, Manaka
    Ohzeki, Masayuki
    JOURNAL OF PHYSICS A-MATHEMATICAL AND THEORETICAL, 2025, 58 (04)
  • [50] A New Technique for Restricted Boltzmann Machine Learning
    Golovko, Vladimir
    Kroshchanka, Aliaksandr
    Turchenko, Volodymyr
    Jankowski, Stanislaw
    Treadwell, Douglas
    2015 IEEE 8TH INTERNATIONAL CONFERENCE ON INTELLIGENT DATA ACQUISITION AND ADVANCED COMPUTING SYSTEMS: TECHNOLOGY AND APPLICATIONS (IDAACS), VOLS 1-2, 2015, : 182 - 186