arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.13871cs.LGcs.DCcs.LO
收藏

具有隐态和不可观测变迁的概率系统

Probabilistic Systems with Hidden State and Unobservable Transitions

Universität Duisburg-Essen(杜伊斯堡-埃森大学)

Rebecca Bernemann, Barbara König, Matthias Schaffeld, Torben Weis

摘要:

我们考虑具有隐状态和不可观测转移的概率系统,这是隐马尔可夫模型(Himp)的扩展,特别是允许不可观测的ε-转移(也称为零转移),允许观察者不知道的状态变化。由于ε-环的存在,这个额外的特征使理论复杂化,并且需要仔细地设置相应的概率空间和随机变量。特别是,我们提出了一种算法,用于确定最可能的解释给出了一个观察(广义的Viterbi算法Hacker)和参数学习的方法,适应一个给定的模型的概率的基础上观察(广义的鲍姆-韦尔奇算法)。后一种算法保证了给定的观测值在调整参数后具有更高(或相等)的概率,并且其正确性可以直接从所谓的EM算法导出。

英文摘要:

We consider probabilistic systems with hidden state and unobservable transitions, an extension of Hidden Markov Models (HMMs) that in particular admits unobservable ε-transitions (also called null transitions), allowing state changes of which the observer is unaware. Due to the presence of ε-loops this additional feature complicates the theory and requires to carefully set up the corresponding probability space and random variables. In particular we present an algorithm for determining the most probable explanation given an observation (a generalization of the Viterbi algorithm for HMMs) and a method for parameter learning that adapts the probabilities of a given model based on an observation (a generalization of the Baum-Welch algorithm). The latter algorithm guarantees that the given observation has a higher (or equal) probability after adjustment of the parameters and its correctness can be derived directly from the so-called EM algorithm.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑