摘要 Local causal states are latent representations th

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

論文資訊

• 類型：已發表論文
• 日期：2020

摘要

Local causal states are latent representations that capture organized pattern and structure in complex spatiotemporal systems. We expand their functionality, framing them as spacetime autoencoders. Previously, they were only considered as maps from observable spacetime fields to latent local causal state fields. Here, we show that there is a 隨機 decoding that maps back from the latent fields to observable fields. Furthermore, their 馬可夫ian properties define a 隨機 dynamic in the latent space. Combined with 隨機 decoding, this gives a new method for forecasting spacetime fields.

※ 此為已發表論文，全文需透過期刊付費取得