PARAMETER-ESTIMATION OF DEPENDENCE TREE MODELS USING THE EM ALGORITHM
PARAMETER-ESTIMATION OF DEPENDENCE TREE MODELS USING THE EM ALGORITHM
复制标题
DOI：
10.1109/97.404132
复制
发表时间：
1995-08-01
影响因子：
3.9
通讯作者：
OSTENDORF, M
中科院分区：
文献类型：
--
作者：
RONEN, O;ROHLICEK, JR;OSTENDORF, M
依赖树是n维随机向量的联合概率分布的模型，通过对树进行类马尔可夫假设，需要相对较少数量的自由参数。在这封信中，我们使用期望最大化算法解决了具有缺失观测值的依赖树模型的最大似然估计问题。该解决方案涉及使用迭代的“向上-向下”算法计算观察概率，该算法类似于为因果树（贝叶斯网络的一种特例）中的置信传播提出的算法。
A dependence tree is a model for the joint probability distribution of an n-dimensional random vector, which requires a relatively small number of free parameters by making Markov-like assumptions on the tree. In this letter, we address the problem of maximum likelihood estimation of dependence tree models with missing observations, using the expectation-maximization algorithm. The solution involves computing observation probabilities with an iterative ''upward-downward'' algorithm, which is similar to an algorithm proposed for belief propagation in causal trees, a special case of Bayesian networks.