English

Decreasing the size of the Restricted Boltzmann machine

Machine Learning 2018-12-13 v2 Machine Learning

Abstract

We propose a method to decrease the number of hidden units of the restricted Boltzmann machine while avoiding decrease of the performance measured by the Kullback-Leibler divergence. Then, we demonstrate our algorithm by using numerical simulations.

Keywords

Cite

@article{arxiv.1807.02999,
  title  = {Decreasing the size of the Restricted Boltzmann machine},
  author = {Yohei Saito and Takuya Kato},
  journal= {arXiv preprint arXiv:1807.02999},
  year   = {2018}
}