A Novel Inference of a Restricted Boltzmann Machine

  title={A Novel Inference of a Restricted Boltzmann Machine},
  author={Masayuki Tanaka and Masatoshi Okutomi},
  journal={2014 22nd International Conference on Pattern Recognition},
A deep neural network (DNN) pre-trained via stacking restricted Boltzmann machines (RBMs) demonstrates high performance. The binary RBM is usually used to construct the DNN. However, a continuous probability of each node is used as real value state, although the state of the binary RBM's node should be represented by a random binary variable. One of main reasons of this abuse is that it works. One of others is to reduce a computational cost. In this paper, we propose a novel inference of the… CONTINUE READING
Highly Cited
This paper has 46 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 22 extracted citations

Deep neural network approach to frog species recognition

2017 IEEE 13th International Colloquium on Signal Processing & its Applications (CSPA) • 2017
View 5 Excerpts
Highly Influenced

Interval type-2 fuzzy sets for enhanced learning in deep belief networks

2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) • 2017
View 3 Excerpts
Highly Influenced

Perturbation Training for Human-Robot Teams

J. Artif. Intell. Res. • 2017
View 4 Excerpts
Highly Influenced


Publications referenced by this paper.
Showing 1-10 of 16 references

Fast dropout training

View 6 Excerpts
Highly Influenced

Modeling Natural Images Using Gated MRFs

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2013
View 1 Excerpt

A Practical Guide to Training Restricted Boltzmann Machines

Neural Networks: Tricks of the Trade • 2012
View 2 Excerpts

Why Does Unsupervised Pre-training Help Deep Learning?

Journal of Machine Learning Research • 2010
View 2 Excerpts

80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2008
View 1 Excerpt

Similar Papers

Loading similar papers…