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：2016-03-02
摘要
Identifying and quantifying memory are often critical steps in developing a mechanistic understanding of 隨機 processes. These are particularly challenging and necessary when exploring processes that exhibit long-range correlations. The most common signatures employed rely on second-order temporal statistics and lead, for example, to identifying long memory in processes with power-law autocorrelation function and Hurst exponent greater than 1/2. However, most 隨機 processes hide their memory in higher-order temporal correlations. 資訊 measures specifically, divergences in the mutual 資訊 between a process' past and future (excess 熵) and minimal predictive memory stored in a process' causal states (統計 complexity) provide a different way to identify long memory in processes with higher-order tempora
※ 此為已發表論文，全文需透過期刊付費取得