摘要 We introduce the minimal maximally predictive mod

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

• SFI 頁面
• DOI

論文資訊

• 類型：已發表論文
• 日期：2017-04-22

摘要

We introduce the minimal maximally predictive models (epsilon-machines) of processes generated by certain hidden semi-馬可夫 models. Their causal states are either discrete, mixed, or continuous random variables and causal-state transitions are described by partial differential equations. As an application, we present a complete analysis of the epsilon-machines of continuous-time renewal processes. This leads to closed-form expressions for their 熵 rate, 統計 complexity, excess 熵, and differential 資訊 anatomy rates.

※ 此為已發表論文，全文需透過期刊付費取得