Training restricted Boltzmann machines: An introduction

@article{Fischer2014TrainingRB,
  title={Training restricted Boltzmann machines: An introduction},
  author={Asja Fischer and C. Igel},
  journal={Pattern Recognit.},
  year={2014},
  volume={47},
  pages={25-39}
}
  • Asja Fischer, C. Igel
  • Published 2014
  • Computer Science
  • Pattern Recognit.
  • Restricted Boltzmann machines (RBMs) are probabilistic graphical models that can be interpreted as stochastic neural networks. [...] Key Method Different learning algorithms for RBMs, including contrastive divergence learning and parallel tempering, are discussed. As sampling from RBMs, and therefore also most of their learning algorithms, are based on Markov chain Monte Carlo (MCMC) methods, an introduction to Markov chains and MCMC techniques is provided. Experiments demonstrate relevant aspects of RBM…Expand Abstract
    Training Restricted Boltzmann Machines
    • 25
    • PDF
    Temperature based Restricted Boltzmann Machines
    • 20
    • PDF
    A bound for the convergence rate of parallel tempering for sampling restricted Boltzmann machines
    • 10
    • PDF
    Restricted Boltzmann Machines: Introduction and Review
    • 14
    • PDF
    Graph Regularized Restricted Boltzmann Machine
    • 27
    • PDF
    On better training the infinite restricted Boltzmann machines
    • 7
    • PDF
    Fuzzy Restricted Boltzmann Machine for the Enhancement of Deep Learning
    • 114

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 132 REFERENCES
    An Introduction to Restricted Boltzmann Machines
    • 367
    • PDF
    Learning Algorithms for the Classification Restricted Boltzmann Machine
    • 220
    • Highly Influential
    • PDF
    On the quantitative analysis of deep belief networks
    • 404
    • Highly Influential
    • PDF
    Deep Boltzmann Machines
    • 1,701
    • PDF
    Investigating Convergence of Restricted Boltzmann Machine Learning
    • 37
    • PDF