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：2009
摘要
Given an observed 隨機 process, 計算 mechanics provides an explicit and efficient method of constructing a minimal hidden 馬可夫 model within the class of maximally predictive models. Here, the corresponding so-called epsilon-machine encodes the mechanisms of prediction. We propose an alternative notion of predictive models in terms of a hidden 馬可夫 model capable of generating the underlying 隨機 process. A comparison of these two notions of prediction reveals that our approach is less restrictive and thereby allows for predictive models that are more concise than the epsilon-machine.
※ 此為已發表論文，全文需透過期刊付費取得