Search results
Education & Career History. Undergrad student. Peking University (pku.edu.cn) 2022 – 2024. Undergrad student. University of California, Berkeley (berkeley.edu) 2023 – 2023.
Dec 8, 2023 · Yiheng Du, Nithin Chalapathi, Aditi Krishnapriyan. We present Neural Spectral Methods, a technique to solve parametric Partial Differential Equations (PDEs), grounded in classical spectral methods. Our method uses orthogonal bases to learn PDE solutions as mappings between spectral coefficients.
- arXiv:2312.05225 [cs.LG]
- Machine Learning (cs.LG)
Yi-Heng Du. S Shen, L Deng, Y Du, J Gao, C Zhang, Y Wang, Z Shen, Y Li, X Chen, ... Psychromarinibacter sediminicola sp. nov., a novel moderately halophilic, metabolically diverse bacterium...
Yiheng DU, Postdoc | Cited by 82 | of Swedish Meteorological and Hydrological Institute, Norrköping (SMHI) | Read 12 publications | Contact Yiheng DU.
Oct 5, 2021 · Expertise. Present and future precipitation variations. Short duration rainfall analysis. Hydrological modelling. Email Yiheng Du about this content. CV (139 kB, pdf) PhD.
Yiheng Du Nithin Chalapathi Aditi S. Krishnapriyan. {yihengdu, nithinc, aditik1}@berkeley.edu. University of California, Berkeley. ABSTRACT. We present Neural Spectral Methods, a technique to solve parametric Partial Dif-ferential Equations (PDEs), grounded in classical spectral methods.
{nithinc, yihengdu, aditik1}@berkeley.edu. University of California, Berkeley. ABSTRACT. Imposing known physical constraints, such as conservation laws, during neural network training introduces an inductive bias that can improve accuracy, reliabil-ity, convergence, and data eficiency for modeling physical dynamics.
