Composite likelihood estimation for restricted Boltzmann machines
Composite likelihood estimation for restricted Boltzmann machines
复制标题
DOI：
--
复制
发表时间：
2012-11
期刊：
影响因子：
--
通讯作者：
Muneki Yasuda;Shun'ichi Kataoka;Yuji Waizumi;Kazuyuki Tanaka
中科院分区：
文献类型：
--
作者：
Muneki Yasuda;Shun'ichi Kataoka;Yuji Waizumi;Kazuyuki Tanaka
通常，使用最大似然估计来学习图形模型的参数是困难的，并且需要近似。最大复合似然估计是最大似然估计的统计近似，是最大伪似然估计的高阶推广。本文提出了一种复合似然方法，并研究了它的性质。此外，我们将其应用于受限制的Boltzmann机器。
Generally, learning the parameters of graphical models by using the maximum likelihood estimation is difficult and requires an approximation. Maximum composite likelihood estimations are statistical approximations of the maximum likelihood estimation and are higher-order generalizations of the maximum pseudo-likelihood estimation. In this paper, we propose a composite likelihood method and investigate its properties. Furthermore, we apply this to restricted Boltzmann machines.