Approximate Learning Algorithm for Restricted Boltzmann Machines
Approximate Learning Algorithm for Restricted Boltzmann Machines
复制标题
DOI：
10.1109/cimca.2008.57
复制
发表时间：
2008-12
期刊：
影响因子：
--
通讯作者：
Muneki Yasuda;Kazuyuki Tanaka
中科院分区：
文献类型：
--
作者：
Muneki Yasuda;Kazuyuki Tanaka
受限玻尔兹曼机由一层可见单元和一层隐藏单元组成，没有可见-可见或隐藏-隐藏连接。受限玻尔兹曼机是构建深度信念网络的主要组成部分，已经被许多研究者所研究。然而，限制玻尔兹曼机的学习算法是一个NP-困难的问题。在本文中，我们提出了一个新的近似学习算法的限制玻尔兹曼机使用EM算法和循环的信念传播。
A restricted Boltzmann machine consists of a layer of visible units and a layer of hidden units with no visible-visible or hidden-hidden connections. The restricted Boltzmann machine is the main component used in building up the deep belief network and has been studied by many researchers. However, the learning algorithm for the restricted Boltzmann machine is a NP-hard problem in general. In this paper we propose a new approximate learning algorithm for the restricted Boltzmann machines using the EM algorithm and the loopy belief propagation.