本頁只刊出中文翻譯與中文說明；英文原文請見下方原文連結。
原文連結
論文資訊
- 類型：已發表論文
- 日期：2020
摘要
Hidden 馬可夫 chains are widely applied 統計 models of 隨機 processes, from fundamental physics and chemistry to finance, health, and 人工智慧. The hidden 馬可夫 processes they generate are notoriously complicated, however, even if the chain is finite state: no finite expression for their Shannon 熵 rate exists, as the set of their predictive features is generically infinite. As such, to date one cannot make general statements about how random they are nor how structured. Here, we address the first part of this challenge by showing how to efficiently and accurately calculate their 熵 rates. We also show how this method gives the minimal set of infinite predictive features. A sequel addresses the challenge's second part on structure.
※ 此為已發表論文，全文需透過期刊付費取得