Restricted Boltzmann Machine with Multivalued Hidden Variables
Restricted Boltzmann Machine with Multivalued Hidden Variables
复制标题
具有多值隐变量的受限玻尔兹曼机
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Muneki Yasuda
中科院分区：
文献类型：
--
作者：
Yuuki Yokoyama;Tomu Katsumata;Muneki Yasuda
泛化是机器学习问题中最重要的问题之一。在本研究中，我们考虑了受限玻尔兹曼机（rbm）中的泛化问题。本文提出了一种具有多值隐变量的RBM，它是传统RBM的一个简单扩展。通过对人工数据对比发散学习和MNIST分类问题的数值实验，证明了该模型优于传统模型。
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.