Restricted Boltzmann Machine with Multivalued Hidden Variables A Model Suppressing Over-Fitting

被引：6
|
作者：
Yokoyama, Yuuki [1 ]
Katsumata, Tomu [2 ]
Yasuda, Muneki [2 ]
机构：
[1] ALBERT Inc, Tokyo, Japan
[2] Yamagata Univ, Grad Sch Sci & Engn, Yamagata, Japan
来源：
REVIEW OF SOCIONETWORK STRATEGIES | 2019年 / 13卷 / 02期
关键词：
Statistical machine learning; Restricted Boltzmann machine; Pattern recognition; Generalization; LEARNING ALGORITHM;
D O I：
10.1007/s12626-019-00042-4
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Generalization is one of the most important issues in machine learning problems. In this study, we consider generalization in restricted Boltzmann machines (RBMs). We propose an RBM with multivalued hidden variables, which is a simple extension of conventional RBMs. We demonstrate that the proposed model is better than the conventional model via numerical experiments for contrastive divergence learning with artificial data and a classification problem with MNIST.
引用
收藏
页码：253 / 266
页数：14
相关论文
共 50 条
  • [1] Restricted Boltzmann Machine with Multivalued Hidden VariablesA Model Suppressing Over-Fitting
    Yuuki Yokoyama
    Tomu Katsumata
    Muneki Yasuda
    [J]. The Review of Socionetwork Strategies, 2019, 13 : 253 - 266
  • [2] Machine learning models and over-fitting considerations
    Charilaou, Paris
    Battat, Robert
    [J]. WORLD JOURNAL OF GASTROENTEROLOGY, 2022, 28 (05) : 605 - 607
  • [3] Machine learning models and over-fitting considerations
    Paris Charilaou
    Robert Battat
    [J]. World Journal of Gastroenterology, 2022, (05) : 605 - 607
  • [4] Sparse hidden units activation in Restricted Boltzmann Machine
    Tomczak, Jakub M.
    Gonczarek, Adam
    [J]. PROGRESS IN SYSTEMS ENGINEERING, 2015, 366 : 181 - 185
  • [5] Policy evaluation using model over-fitting: the Nordic case
    Tapia, Armando
    Gonzalez, Silvestre L. L.
    Vergara, Jose R. R.
    Villafuerte, Mariano
    Montiel, Luis V. V.
    [J]. COMPUTATIONAL STATISTICS, 2023,
  • [6] On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation
    Cawley, Gavin C.
    Talbot, Nicola L. C.
    [J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2010, 11 : 2079 - 2107
  • [7] Under-Fitting and Over-Fitting: The Performance of Bayesian Model Selection and Fit Indices in SEM
    Depaoli, Sarah
    Winter, Sonja D.
    Liu, Haiyan
    [J]. STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL, 2024, 31 (04) : 604 - 625
  • [8] On over-fitting in model selection and subsequent selection bias in performance evaluation
    Cawley, Gavin C.
    Talbot, Nicola L. C.
    [J]. Journal of Machine Learning Research, 2010, 11 : 2079 - 2107
  • [9] Study of the Over-Fitting in Building PLS Model Using Orthogonal Signal Correction
    Zhang Xian
    Yuan Hong-fu
    Guo Zheng
    Song Chun-feng
    Li Xiao-yu
    Xie Jin-chun
    [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2011, 31 (06) : 1688 - 1691
  • [10] Agricultural Case Studies of Classification Accuracy, Spectral Resolution, and Model Over-Fitting
    Nansen, Christian
    Geremias, Leandro Delalibera
    Xue, Yingen
    Huang, Fangneng
    Parra, Jose Roberto
    [J]. APPLIED SPECTROSCOPY, 2013, 67 (11) : 1332 - 1338
12345