Approximate Learning Algorithm for Restricted Boltzmann Machines

被引：5
|
作者：
Yasuda, Muneki [1 ]
Tanaka, Kazuyuki [1 ]
机构：
[1] Tohoku Univ, Grad Sch Informat Sci, Aoba Ku, Sendai, Miyagi 9808579, Japan
来源：
2008 INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE FOR MODELLING CONTROL & AUTOMATION, VOLS 1 AND 2 | 2008年
关键词：
D O I：
10.1109/CIMCA.2008.57
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
A restricted Boltzmann machine consists of a layer of visible units and a layer of hidden units with no visible-visible or hidden-hidden connections. The restricted Boltzmann machine is the main component used in building up the deep belief network and has been studied by many researchers. However, the learning algorithm for the restricted Boltzmann machine is a NP-hard problem in general. In this paper we propose a new approximate learning algorithm for the restricted Boltzmann machines using the EM algorithm and the loopy belief propagation.
引用
收藏
页码：692 / 697
页数：6
相关论文
共 50 条
  • [1] Approximate Learning Algorithm in Boltzmann Machines
    Yasuda, Muneki
    Tanaka, Kazuyuki
    [J]. NEURAL COMPUTATION, 2009, 21 (11) : 3130 - 3178
  • [2] SCALABLE LEARNING FOR RESTRICTED BOLTZMANN MACHINES
    Barshan, Elnaz
    Fieguth, Paul
    [J]. 2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2014, : 2754 - 2758
  • [3] A LEARNING ALGORITHM FOR BOLTZMANN MACHINES
    ACKLEY, DH
    HINTON, GE
    SEJNOWSKI, TJ
    [J]. COGNITIVE SCIENCE, 1985, 9 (01) : 147 - 169
  • [4] Spectral dynamics of learning in restricted Boltzmann machines
    Decelle, A.
    Fissore, G.
    Furtlehner, C.
    [J]. EPL, 2017, 119 (06)
  • [5] Neurosymbolic Reasoning and Learning with Restricted Boltzmann Machines
    Tran, Son N.
    Garcez, Artur d'Avila
    [J]. THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 5, 2023, : 6558 - 6565
  • [6] An Incremental Learning Approach for Restricted Boltzmann Machines
    Yu, Jongmin
    Gwak, Jeonghwan
    Lee, Sejeong
    Jeon, Moongu
    [J]. FOURTH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND INFORMATION SCIENCES (CCAIS 2015), 2015, : 113 - 117
  • [7] Infinite Swapping Algorithm for Training Restricted Boltzmann Machines
    Hult, Henrik
    Nyquist, Pierre
    Ringqvist, Carl
    [J]. MONTE CARLO AND QUASI-MONTE CARLO METHODS, MCQMC 2018, 2020, 324 : 285 - 307
  • [8] Effective learning algorithm for restricted Boltzmann machines via spatial Monte Carlo integration
    Sekimoto, Kaiji
    Yasuda, Muneki
    [J]. IEICE NONLINEAR THEORY AND ITS APPLICATIONS, 2023, 14 (02): : 228 - 241
  • [9] Thermodynamics of Restricted Boltzmann Machines and Related Learning Dynamics
    A. Decelle
    G. Fissore
    C. Furtlehner
    [J]. Journal of Statistical Physics, 2018, 172 : 1576 - 1608
  • [10] LEARNING SPAM FEATURES USING RESTRICTED BOLTZMANN MACHINES
    da Silva, Luis Alexandre
    Pontara da Costa, Kelton Augusto
    Ribeiro, Patricia Bellin
    de Rosa, Gustavo Henrique
    Papa, Joao Paulo
    [J]. IADIS-INTERNATIONAL JOURNAL ON COMPUTER SCIENCE AND INFORMATION SYSTEMS, 2016, 11 (01): : 99 - 114
12345