BriefGPT.xyz
Jul, 2023
DiTTO: 扩散启发的时态变换器操作符
DiTTO: Diffusion-inspired Temporal Transformer Operator
HTML
PDF
Oded Ovadia, Eli Turkel, Adar Kahana, George Em Karniadakis
TL;DR
我们提出了一种名为DiTTO的算子学习方法来连续地解决时间相关的偏微分方程,该方法通过将受扩散模型启发的框架与Transformer架构相结合,实现了在多个维度上的各种PDEs的准确解决,并通过使用扩散模型中的快速采样概念进一步提高了性能,并展示了DiTTO可以在时间上精确执行零短片超分辨率。
Abstract
Solving
partial differential equations
(PDEs) using a data-driven approach has become increasingly common. The recent development of the operator learning paradigm has enabled the solution of a broader range of PDE-related problems. We propose an
→