...
首页> 外文期刊>Entropy >Properties of the Statistical Complexity Functional and Partially Deterministic HMMs
【24h】

Properties of the Statistical Complexity Functional and Partially Deterministic HMMs

机译:统计复杂度函数和部分确定性HMM的性质

获取原文
           

摘要

Statistical complexity is a measure of complexity of discrete-time stationary stochastic processes, which has many applications. We investigate its more abstract properties as a non-linear function of the space of processes and show its close relation to the Knight’s prediction process. We prove lower semi-continuity, concavity, and a formula for the ergodic decomposition of statistical complexity. On the way, we show that the discrete version of the prediction process has a continuous Markov transition. We also prove that, given the past output of a partially deterministic hidden Markov model (HMM), the uncertainty of the internal state is constant over time and knowledge of the internal state gives no additional information on the future output. Using this fact, we show that the causal state distribution is the unique stationary representation on prediction space that may have finite entropy.
机译:统计复杂度是离散时间平稳随机过程的复杂度的一种度量,它具有许多应用。我们将其更抽象的属性作为过程空间的非线性函数进行研究,并显示其与Knight的预测过程的密切关系。我们证明了较低的半连续性,凹度和统计复杂度的遍历分解公式。在途中,我们表明预测过程的离散版本具有连续的马尔可夫过渡。我们还证明,考虑到部分确定性隐式马尔可夫模型(HMM)的过去输出,内部状态的不确定性会随着时间的推移而保持不变,并且内部状态的知识不会为将来的输出提供任何其他信息。利用这一事实,我们证明了因果状态分布是预测空间上唯一的平稳表示,它可能具有有限的熵。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号