On learning parametric-output HMMs
On learning parametric-output HMMs
复制标题
关于学习参数输出 HMM
DOI：
--
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Roi Weiss
中科院分区：
文献类型：
--
作者：
A. Kontorovich;B. Nadler;Roi Weiss
我们提出了一种新的学习隐马尔可夫模型的方法，它的输出是按照一个参数族分布的。这是通过将学习任务解耦为两个步骤来完成的：首先估计输出参数，然后估计隐藏状态转移概率。第一步是通过将混合模型拟合到输出平稳分布来完成的。在给定混合模型参数的情况下，第二步被表示为一个容易求解的凸二次规划的解。我们对估计的转移概率进行了误差分析，并证明了它们对混合参数估计中的微小扰动是稳健的。最后，我们用一些令人鼓舞的实证结果支持了我们的分析。
We present a novel approach for learning an HMM whose outputs are distributed according to a parametric family. This is done by {\em decoupling} the learning task into two steps: first estimating the output parameters, and then estimating the hidden states transition probabilities. The first step is accomplished by fitting a mixture model to the output stationary distribution. Given the parameters of this mixture model, the second step is formulated as the solution of an easily solvable convex quadratic program. We provide an error analysis for the estimated transition probabilities and show they are robust to small perturbations in the estimates of the mixture parameters. Finally, we support our analysis with some encouraging empirical results.