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
  • [21] Complete Mean-Field Theory for Dynamics of Binary Recurrent Networks
    Farkhooi, Farzad
    Stannat, Wilhelm
    PHYSICAL REVIEW LETTERS, 2017, 119 (20)
  • [22] Exact diagonalization solver for extended dynamical mean-field theory
    Medvedeva, Darya
    Iskakov, Sergei
    Krien, Friedrich
    Mazurenko, Vladimir V.
    Lichtenstein, Alexander I.
    PHYSICAL REVIEW B, 2017, 96 (23)
  • [23] Fermionic mean-field theory as a tool for studying spin Hamiltonians
    Henderson, Thomas M.
    Harrison, Brent
    Magoulas, Ilias
    Necaise, Jason
    Projansky, Andrew M.
    Evangelista, Francesco A.
    Whitfield, James D.
    Scuseria, Gustavo E.
    JOURNAL OF CHEMICAL PHYSICS, 2024, 161 (23)
  • [24] Mean-field theory of collective motion due to velocity alignment
    Romanczuk, Pawel
    Schimansky-Geier, Lutz
    ECOLOGICAL COMPLEXITY, 2012, 10 : 83 - 92
  • [25] Entanglement mean-field theory and the Curie-Weiss law
    Sen , Aditi
    Sen, Ujjwal
    EPL, 2012, 99 (02)
  • [26] Mean-Field Theory for the Inverse Ising Problem at Low Temperatures
    Nguyen, H. Chau
    Berg, Johannes
    PHYSICAL REVIEW LETTERS, 2012, 109 (05)
  • [27] Modulation effects within the mean-field theory of electrolyte solutions
    Landy, Jonathan
    PHYSICAL REVIEW E, 2010, 81 (01):
  • [28] Surface tension of a Yukawa fluid according to mean-field theory
    Bossa, Guilherme Volpe
    Norris, Joseph
    May, Sylvio
    JOURNAL OF CHEMICAL PHYSICS, 2017, 146 (13)
  • [29] Dynamical mean-field theory: from ecosystems to reaction networks
    De Giuli, Eric
    Scalliet, Camille
    JOURNAL OF PHYSICS A-MATHEMATICAL AND THEORETICAL, 2022, 55 (47)
  • [30] Application of the complex scaling method in relativistic mean-field theory
    Guo, Jian-You
    Fang, Xiang-Zheng
    Jiao, Peng
    Wang, Jing
    Yao, Bao-Mei
    PHYSICAL REVIEW C, 2010, 82 (03):