Restricted Boltzmann Machine with Multivalued Hidden Variables: a model suppressing over-fitting
Machine Learning
2020-01-09 v4 Machine Learning
Abstract
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.
Cite
@article{arxiv.1811.12587,
title = {Restricted Boltzmann Machine with Multivalued Hidden Variables: a model suppressing over-fitting},
author = {Yuuki Yokoyama and Tomu Katsumata and Muneki Yasuda},
journal= {arXiv preprint arXiv:1811.12587},
year = {2020}
}