Zobrazeno 1 - 10
of 505
pro vyhledávání: '"Long DA"'
Modern physics simulation often involves multiple functions of interests, and traditional numerical approaches are known to be complex and computationally costly. While machine learning-based surrogate models can offer significant cost reductions, mo
Externí odkaz:
http://arxiv.org/abs/2410.13794
This paper introduces a novel kernel learning framework toward efficiently solving nonlinear partial differential equations (PDEs). In contrast to the state-of-the-art kernel solver that embeds differential operators within kernels, posing challenges
Externí odkaz:
http://arxiv.org/abs/2410.11165
Autor:
Long, Da, Zhe, Shandian
Fourier Neural Operator (FNO) is a popular operator learning method, which has demonstrated state-of-the-art performance across many tasks. However, FNO is mainly used in forward prediction, yet a large family of applications rely on solving inverse
Externí odkaz:
http://arxiv.org/abs/2402.11722
Chiral molecule assignation is crucial for asymmetric catalysis, functional materials, and the drug industry. The conventional approach requires theoretical calculations of electronic circular dichroism (ECD) spectra, which is time-consuming and cost
Externí odkaz:
http://arxiv.org/abs/2401.03403
Publikováno v:
The Twelfth International Conference on Learning Representations (ICLR 2024)
Machine learning based solvers have garnered much attention in physical simulation and scientific computing, with a prominent example, physics-informed neural networks (PINNs). However, PINNs often struggle to solve high-frequency and multi-scale PDE
Externí odkaz:
http://arxiv.org/abs/2311.04465
Autor:
Long, Da, Xing, Wei W., Krishnapriyan, Aditi S., Kirby, Robert M., Zhe, Shandian, Mahoney, Michael W.
Discovering governing equations from data is important to many scientific and engineering applications. Despite promising successes, existing methods are still challenged by data sparsity and noise issues, both of which are ubiquitous in practice. Mo
Externí odkaz:
http://arxiv.org/abs/2310.05387
This article presents a three-step framework for learning and solving partial differential equations (PDEs) using kernel methods. Given a training set consisting of pairs of noisy PDE solutions and source/boundary terms on a mesh, kernel smoothing is
Externí odkaz:
http://arxiv.org/abs/2210.08140
Physical modeling is critical for many modern science and engineering applications. From a data science or machine learning perspective, where more domain-agnostic, data-driven models are pervasive, physical knowledge -- often expressed as differenti
Externí odkaz:
http://arxiv.org/abs/2202.12316
Publikováno v:
In Physica D: Nonlinear Phenomena April 2024 460
Autor:
Xue Yi-Jun, Xiao Ri-Hai, Long Da-Zhi, Zou Xiao-Feng, Wang Xiao-Ning, Zhang Guo-Xi, Yuan Yuan-Hu, Wu Geng-Qing, Yang Jun, Wu Yu-Ting, Xu Hui, Liu Fo-Lin, Liu Min
Publikováno v:
Journal of Translational Medicine, Vol 10, Iss 1, p 200 (2012)
Abstract Background Fork head box M1 (FoxM1) is a proliferation-associated transcription factor essential for cell cycle progression. Numerous studies have documented that FoxM1 has multiple functions in tumorigenesis and its elevated levels are freq
Externí odkaz:
https://doaj.org/article/32756f7b380c4e8080b690d5695a0005