Reproduce “PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zichao Long, Yiping Lu, Bin Dong
PDE-Net 2.0 learns convolution filters that approximate spatial derivatives and a multiplication-based symbolic network that combines them into an inspectable update rule for evolving fields. In noisy simulated two-dimensional Burgers’ equation data, it recovered the main equation terms and had lower forecast errors than a version with fixed filters across 1,000 initial conditions, through t=4; these results concern simulated data.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.