BriefGPT.xyz
May, 2024
动力系统的循环深度核学习
Recurrent Deep Kernel Learning of Dynamical Systems
HTML
PDF
Nicolò Botteghi, Paolo Motta, Andrea Manzoni, Paolo Zunino, Mengwu Guo
TL;DR
使用基于数据驱动的随机变分深度核学习以及递归版本，提出了一种构建ROMs的方法，能够对物理资产的复杂动态进行精确描述，并具备去噪、重建、学习紧凑表征系统状态、预测以及量化建模不确定性的能力。
Abstract
digital twins
require computationally-efficient
reduced-order models
(ROMs) that can accurately describe complex dynamics of physical assets. However, constructing ROMs from noisy high-dimensional data is challen
→