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：2025-04-25
摘要
Pervasive across diverse domains, 隨機 systems exhibit fluctuations in processes ranging from molecular dynamics to 氣候 phenomena. The Langevin equation has served as a common 數學 model for studying such systems, enabling predictions of their temporal 演化 and analyses of 熱力學 quantities, including absorbed heat, work done on the system, and 熵 production. However, inferring the Langevin equation from observed trajectories is a challenging problem, and assessing the uncertainty associated with the inferred equation has yet to be accomplished. In this study, we present a comprehensive framework that employs 貝氏 神經 網絡s for inferring Langevin equations in both overdamped and underdamped regimes. Our framework first provides the drift force and 擴散 matrix separately and then combines them to construct t
※ 此為已發表論文，全文需透過期刊付費取得